The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Aware agents (A-agents) are systems that can be aware of user intention, preference, situation, etc., and can provide proper solutions. To support user's daily lives, we try to implement A-agents in portable/wearable computing devices (P/WCDs). However, a P/WCD usually does not have enough computing resource and battery to implement high performance A-agents. Cloud computing is a technology to augment...
Multilayer perceptrons (MLPs) have been successfully applied to solving many problems, but in most cases, they are used as black boxes which are not interpretable. That is, even if an MLP can provide correct answers, we cannot understand the reasons why it makes these decisions. In this study, we try to interpret a single hidden layer MLP by discretizing the hidden neuron outputs into 3 values (e...
This paper studies the possibility of recognizing resident locations and activities using an infrared sensor array. In our study, we try to build smart homes that are smart enough to help the residents, and at the same time, stupid enough not to touch the resident privacy. For this purpose, we try to use a sparse infrared sensor array to recognize some frequently appeared locations/activities that...
Big data, the Internet of Things, Industry 4.0, and automatic car driving are several current hot topics, and artificial intelligence (AI) is behind each of them. AI is now supported by both governments and private companies. The overall trend is positive; however, it seems that we are relying too much on money, resources, and power. To create AI that can solve all kinds of problems efficiently and...
In this paper, we propose a privacy preserving protocol for cloud system utilization based on extreme learning machine (ELM). The purpose is to implement aware agents (A-agents) on portable/wearable computing devices (P/WCD). The proposed protocol is useful to reduce the calculation cost on the P/WCD. The basic idea of the protocol is to divide an ELM-based A-agent into two parts, one containing the...
To retrain an existing multilayer perceptron (MLP) on-line using newly observed data, it is necessary to incorporate the new information while preserving the performance of the network. This is known as the “plasticitystability” problem. For this purpose, we proposed an algorithm for on-line training with guide data (OLTA-GD). OLTA-GD is good for implementation in portable/wearable computing devices...
Biometric authentication (BA) is becoming more and more popular. Usually, we expect that BA can make various service systems more secure, but in fact it can be more dangerous. For example, fingerprint is one of the popular biometrics for authentication. We say it is dangerous because we cannot change our fingerprints even if they are collected and duplicated by some malicious third parties. This kind...
In this paper, we propose a method for generating guide data, and investigate its efficiency and efficacy for on-line learning with guide data. On-line learning in this research updates a learning model initialized by the decision boundary making algorithm proposed by us in our earlier study. The problem is that, if the guide data are not properly generated, on-line learning may require high computational...
We compare the performance of multilayer perceptrons (MLPs) obtained using back propagation (BP), decision boundary making (DBM) algorithm and extreme learning machine (ELM), and investigate better method for developing aware agents (A-agent) that are suitable for implementation in portable/wearable computing devices (P/WCD). The DBM has been proposed by us for inducing compact and high performance...
In recent years, researches on smart environments (SEs) especially smart homes for senior care have attracted great attention. One important issue in constructing such kind of SEs is privacy, because the target environment (e.g. a home or a room) is not public space, and devices like video cameras cannot be used. For individual or personal spaces, the SE should not be too smart to invade the resident's...
The main purpose of computational awareness (CA) is to make our human beings more aware. A well designed aware system should be able to detect novel events, inform us when the events occur, and tell us what to do. In many cases, we may not trust the machine. We want to know the reasons why the event is novel, and why we should take certain actions if an event is observed. For this purpose, it is important...
Smart environment is a situation aware system for improving the quality of life. This kind of systems are extremely useful for solving or avoiding several issues. The issue we consider in this research is the care of elderly peoples living in their own homes. Usually, information needed for situation awareness is obtained from various devices such as video cameras and voice recorders. However, these...
We human beings are often careless, forgetful and ignorant. We often miss good timing for capturing chances or avoiding risks. Computational awareness (CA) can help us to be more aware. An aware system can distinguish novel events from normal ones, inform us when the novel events are detected, and tell us the correct reaction. In many cases, we are interested in knowing reasons why certain situations...
In recent years, concern about information security is increasing. Image-based steganography is an information hiding technique for improving information security. Its purpose is to conceal the existence of secret data. Recently, a stego-image detection scheme was proposed in the literature, which uses the so called extreme learning machine and features generated by Markov chain. Verification results...
Awareness is a way from sensory data to cognition. The main purpose of computational awareness (CA) is to understand the awareness mechanism and realize it in computers. Various awareness are used in our daily lives for making decisions, but most of them are tacit. For the purpose of CA, we need to interpret and understand tacit awareness as far as possible. In our earlier study, we introduced a general...
The main purpose of smart environment (SE) is to assist human daily lives by analyzing and recognizing related information. Usually, equipments such as video cameras and voice recorders are useful to capture the information. However, the data often contain unnecessary information related to privacy. To solve this problem, it is important to construct SE by using simple sensors like motion sensor,...
In this paper, we investigate proper strategies for determining the step size of the backpropagation (BP) algorithm for on-line learning. It is known that for off-line learning, the step size can be determined adaptively during learning. For on-line learning, since the same data may never appear again, we cannot use the same strategy proposed for off-line learning. If we do not update the neural network...
Research results on medicine and health show that people nowadays tend to have some common diseases because of abnormal eating habits, irregular lifestyles, fast-food culture, etc. Diabetes and high blood pressure are just two examples. This study is based on an ontology-based dietary management system established by our group earlier. The main contribution of this paper is to propose a method for...
It is known that images seen by human eyes and those captured by camera lens are evidently different. In general, a human eye can see the majority of the view field. However, a lens has limited visual range due to various specifications and uses. We can obtain a panoramic image that has a wider view field using stitching techniques from input images captured by putting the lens in different view angles...
Smart environment enriches resident's lives by assisting the residents in many situations via recognition of their activities. Some equipment such as video camera are often used for collecting the resident activity information. However, the data so collected also include extra information not necessary for assisting resident's lives. Many people feel uncomfortable with these privacy related data....
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.