Power suppliers generate electricity to ensure that the power generated equals demand. The vast daily fluctuations in electricity demand result in very high generation costs. Demand response is attracting attention as a solution to these problems in recent years with the spread of renewable energy, energy resources such as storage batteries, and the development of IoT technologies. Demand response means changing the power demand pattern by controlling demand side energy resources and distributed energy resources. In recent years, the use of demand response and the construction of mechanisms for it are being promoted. In this study, we focus on negawatt trading that is one of the demand response policies. We formulate a stochastic programming model for negawatt planning operation and the efficient solution method are shown. From experiment results, it is shown that the worst situation can be avoided using CVaR model. We also showed the efficiency of solution.

In 2017, it became mandatory for universities in Japan to disclose their policies in degree granting (Diploma Policy: DP, hereafter) that state standards to confer degrees. Meanwhile, since 1991, nomenclature of major fields that appear in diplomas has been the responsibility of individual universities, instead of the national regulation. This study examines whether the former reasonably evokes the latter, given that both of them are deemed to represent the learning outcomes that the graduate has obtained. In order to do so, we compared the ability of humans and that of a deep-learning system (which is based on the Character-level CNN), to match DPs and major fields that are randomly given. In the examination of human ability, which was implemented with a large enough number of participants to obtain statistically significant results, we found there were a certain number of DPs that the majority of people failed to match with major fields. Given this fact, we analyzed such DPs to demonstrate that the deep learning system shows a high success rate in sorting out the DPs that poorly evoke major fields.

Multi-package type air-conditioning systems are installed in various offices. Generally, those systems are operated in such a way that the heating or cooling modes, temperature, and air volume can be set arbitrarily. Even if the room temperatures and air flows are reasonable, the thermal environments are not clear whether it is comfortable for persons in the rooms.

Our goal is to build an automatic control system for individual air conditioning by using IoT devices and machine learning. Therefore, as a first effort, this paper proposes to focus on the prediction performance of machine learning and to build a thermal comfort level estimation model to predict the comfort level of humans in a room.

To solve the last mile problem in rural areas, we deal with compact ride-sharing model. For reducing the computational cost, we use a simple GA method and compared the performance of the parameters. To simplify the problem, our algorithm use a simple linear distance and minimize the total traveling distance. A data set used for GA was based on the Inami area in Nanto City, Toyama Prefecture, that is a real case study region. The performance comparison experiment of the algorithm by changing parameters was carried out. Experimental results show that the algorithm is likely to give correct answers for up to four vehicles. It was also shown that the combination of population size and elite proportion for GA could reduce computational costs while ensuring accuracy. In addition, by ride-sharing was actually carried out using the obtained experimental result, it was shown that it could be applied to the actual route even if the calculation was carried out in the linear distance.

In this research Markov decision processes is applied to purchasing strategy with dynamic pricing. A new purchasing strategy which maximizes the total revenue is proposed. In the proposed purchasing strategy a number of products and a price are decided. The effectiveness of the proposed method is shown by some computational examples.

In this research an active learning method for cultivation management using Markov decision processes is proposed. The proposed method is equivalent to a test cultivation method in agricultural experiment stations. The effectiveness of the proposed method is shown by a computational example.

Strömbom et al. elucidated an algorithm in which a sheepdog can skillfully control a flock of sheep to guide them to a destination. This is called the Herding Algorithm, and it models the behavior of a sheepdog in two ways: “driving”, which guides a flock of sheep to a destination, and “collecting”, which brings the sheep together into one flock. In this model, Go et al. showed that an agent (sheepdog) could herd a flock of sheep with an inference model generated by reinforcement learning (RL). However, in their previous study, RL learned only the movement behavior to the positions at which the agent performs “driving” and “collecting” in the discretized environmental state and behavioral space. In this study, we have assumed a continuous environmental state and behavioral space. We have confirmed that even if the agent's herding behavior is the learning target, the proposed inference model generated by deep RL can herd sheep.

Quantum illumination proposed by Lloyd is a protocol that detects the existence of a target by using entangled light of two-mode. Quantum illumination was first proposed using the Bell state, and then the use of a two-mode Gaussian state was proposed. On the other hand, there are many impact studies using the quasi-Bell state. However, as far as we know, there are no studies that analyze quantum illumination using the quasi-Bell state. Therefore, we focused on the performance evaluation of quantum illumination using the quasi-Bell state in this paper. We compared and considered the effects using the Bell state, the two-mode Gaussian state, the maximum quasi-Bell state, the non-maximum quasi-Bell state, and the coherent state (i.e., a laser radar) on the attenuated channel. In particular, we derived the exact solutions of the error probabilities when using the maximum and non-maximum quasi-Bell states. Then we clarified that quantum illumination using the quasi-Bell state offers a clear advantage over that using the other entangled states under almost situations and always offers a clear advantage over the laser radar.

In recent years, various studies using electric vehicles have been conducted against the background of environmental problems and the spread of electric vehicles. The models in these studies are diverse, and have different goals. There are various problems such as minimizing the delivery cost of electric vehicles in the car sharing model and minimizing the cost of electric power when purchasing electric power to charge the electric vehicle. Therefore, in this study, we consider the optimal operation of electric vehicles for the purpose of leveling the load of electric power to multiple houses in the car sharing model. Then, the comparison is made with the case where EV is not used, and output results are analyzed. In addition, load leveling can be achieved with this model, and it has become possible to obtain the amount of power actually required.

In this paper, we propose an estimation method of a starting point of a rally, and a score transition from a table tennis match video. First, a rally scene is estimated from a table tennis video. The rally scene is estimated with utilizing an appearance frequency, and a hue similarity of the rally scene. Next, a server is estimated from the rally scene to analyze a player's posture. In addition, the score transition is estimated from a scoreboard in the rally scene. As a result of an evaluation experiment, the proposed method is used by a table tennis coach, and its contribution is confirmed.

In recent years, the number of drug trafficking using microblogs has been increasing, which has become a social problem. While cyber patrols have been conducted to crack down on such crimes, those who post crime-inducing messages use terms that camouflage their criminal intentions so-called “codewords” to avoid keywords such as “enjo kosai,” “marijuana,” and “methamphetamine” that may be monitored and attract police attention. These codewords change once they become popular, so it is always necessary to keep track of the latest codewords. Therefore, we propose a new method for detecting the latest codewords. In this paper, we offer a new way of detecting code words from the differences in the words used in posts to detect codewords used in a crime. Specifically, we propose a new method in which we divide words into two corpora, depending on whether a post containing a word has a criminal intention and detect codewords from the differences between similar words of the same word between two corpora. To confirm the effectiveness of the proposed method, we conducted an experiment to detect codewords. The experimental results showed that the proposed method was able to detect codewords with an accuracy of 0.56 persentages points higher than that of the baseline method. The experiment shows that the proposed method can reduce the burden of continuously monitoring code words by rapidly and automatically detecting new codewords that change with time; thus, it provides the possibility of showing clues for crimes.

This paper concentrates on parallel queueing systems, called fork-less shaped queueing systems, taking a checkout area of the supermarket as an example. In fork-less shaped queueing systems, customers choose the server with their criterion. Sometimes queue length become imbalanced due to customers freely choices. Imbalanced queue has negative effects on both store clerk and customer, so it is necessary to reduce the variation of queue length. “Shikake” is a method of changing human behavior. It can be possible to reduce the variation of queue length. In this paper, we suggest some reduction Shikake and verify the effects of them using a multi-agent simulation.

This paper proposes the clustering-based optimization method for landing sequence of aircraft, which partitions all the aircraft into several clusters and optimizes the schedules of these parted aircraft in parallel. We conducted the computer simulation of the Charles de Gaulle Airport in France and revealed that (1) our proposed method obtains the feasible optimization solution without conflicts among aircraft for landing sequence and (2) the optimized schedule of the proposed method is the better than that of the conventional method based on the fixed time window (corresponding to the fixed size of clusters of aircraft).

This paper reports on the result of in-home behavioral observation employing Internet of Things (IoT) sensors. Behavioral observation is a qualitative research method used to understand the users' reality of daily activities and the usage of services or products. This method has been mainly utilized in public spaces such as schools and commercial facilities to develop the creative processes. In contrast, this method is difficult to utilize at a household level because problems with existing methods include costs, privacy implications, and the other complications regarding the specific behaviors of the person being observed. An in-home behavioral observation employing IoT sensors is therefore an effective approach to both reduce costs and alleviate the privacy impact on user's in-home activities. The use of sensor-based observation presents several relevant advantages. For example, the cost of sensor-based observation is relatively cheap compared to human-based approaches. In addition, it employs a minimum number of necessary sensors and has a relatively small impact on privacy and personal activities. These advantages imply that this approach could allow long-term observations targeting a number of households, thus enabling exhaustive investigations. Sensory-based observation approaches are applied to investigations of the barriers to in-home energy-saving activities with a goal of improving relevant behavioral change programs. The results showed that the in-home activities of the twenty target households were successfully observed for six weeks with various barriers having been extracted and organized.