The cortical learning algorithm (CLA) is a type of time-series data prediction algorithm based on the human neocortex. CLA uses multiple columns to represent an input data value at a timestep, and each column has multiple cells to represent the time-series context of the input data. In the conventional CLA, the numbers of columns and cells are user-defined parameters. These parameters depend on the input data, which can be unknown before learning. To avoid the necessity for setting these parameters beforehand, in this work, we propose a self-structured CLA that dynamically adjusts the numbers of columns and cells according to the input data. The experimental results using the time-series test inputs of a sine wave, combined sine wave, and logistic map data demonstrate that the proposed self-structured algorithm can dynamically adjust the numbers of columns and cells depending on the input data. Moreover, the prediction accuracy is higher than those of the conventional long short-term memory and CLAs with various fixed numbers of columns and cells. Furthermore, the experimental results on a multistep prediction of real-world power consumption show that the proposed self-structured CLA achieves a higher prediction accuracy than the conventional long short-term memory.
Humor is important in smooth human communications, however, computer-generated humor is still distinguishable from humor that arises naturally in human communication. The purpose of this study is to construct a computer system that can generate humor in a human-like manner. The method involves using “nazokake” riddles, which comprise a type of Japanese word game. The game creates humorous links between two incongruous premises by linking them semantically to homophones: “Why is A like B? Because X/X′,” where A and B are independent premises and X and X′ are homophones linked to A and B, respectively. In a previous study, a system was constructed to generate such riddles based on a simple word similarity between two nouns that are homophones. This study builds on the previous study by generating more complex riddles based on the dependency relationships between homophonic verb-noun combinations. Subsequently, the two systems are compared with each other by evaluating them against riddles created by humans. The results show that the system based on dependency relationships generated more humorous, unexpected, and natural riddles than that based on word similarities. However, these riddles were not equal to those created by humans.
Coverage is a crucial issue in directional sensor networks (DSNs), and a high coverage ratio ensures a good quality of service (QoS). However, a DSN encounters various problems because they use directional sensor nodes, which are characterized by directionality and a definite sensing angle. To address the area coverage problem of DSNs, this paper proposes a new sensing direction rotation approach to optimize coverage. First, we conduct grid partitioning in the target area and propose a coverage verification algorithm to justify the coverage situation of the grid points. Then, we utilize particle swarm optimization (PSO) to find an optimal sensing direction group of the directional sensor nodes to maximize the coverage ratio. Extensive simulation experiments were conducted to prove the effectiveness and reliability of our proposed approach. The results show that the approach improves the area coverage ratio of DSNs in various scenarios.
This paper aims to analyze the lifestyle of residents from household electricity consumption data. Improving QOL (Quality of Life) of elderlies has attracted attention in a super-aging society. It is known that the lifestyle of a person directly affects his / her health and QOL. Therefore, understanding a lifestyle is expected to be useful for providing various support for improving QOL, such as recommending adequate actions and daily habit. As a means for understanding residents’ lifestyle, this paper focuses on household electricity consumption data, which gets to be available with the spread of smart meters. The analysis is conducted by estimating the time of taking essential actions such as wake up and eating. As the target data has no ground truth, this paper also shows the result of an experiment on the detection of the essential actions. The analysis results reveal several findings which could be useful for improving QOL, such as positive correlation between regularity of dinner time and bedtime.
In the combustion process of a coke oven, it is crucial to evaluate the operating state to ensure control performance for the stabilization of the coke oven temperature. This paper presents an assessment method for a coke oven operating state based on the analysis of the mechanism. A coke oven, which is an integrator, is categorized into serial subsystems, which include two coking chambers and one combustion chamber. First, the raw gas temperature of every coking chamber is extracted online and is combined with the qualitative trend analysis that yields the feature point of the raw gas temperature. Subsequently, fuzzy method is presented to describe the uncertainty and evaluate the heat level of each subsystem. Finally, a comprehensive assessment of the operating state of the coke oven is performed by combining the weighted contribution of all subsystems, which is expressed by information entropy. Simulations and experiments demonstrate the validity of the method.
Safety-critical systems (SCS) are the most significant systems that affect our daily life in many areas such as flight control systems, railway systems, medical devices, nuclear systems, and military weapons. SCS failures could result in losing life or serious injuries. Improving the practices during development phases of SCS can reduce failures up to 40%, thus resulting developers to follows specific development practices and techniques. Developers should improve safety-critical system development (SCSD) by taking into account all factors and understanding the causes of failure. Previous studies have highlighted the causes of failure during the development of SCS, but for specific areas such as designs, requirements, or the human factor, while developers need to know the causes of failure in all areas and the relationship between them clearly and comprehensively. This research aims to analyze SCSD characteristics and discuss performance improvement as well as causes of failure. This paper proposed a guideline that helps developers reduce the causes of failure during SCS development. This guide has four characteristics, each with a role in improving SCSD and reducing causes of failure.