Regional public transportation services in Japan, including buses and taxis, face challenges such as crew shortages. This is attributed to a combination of factors: a decline in demand due to the Corona disaster and an aging workforce caused by the inability to attract new crews. Despite these challenges, regional public transportation relies heavily on minimal revenue streams like fixed fares. The primary source of funding is not fare revenue but subsidies from local governments overseeing these services. Consequently, these services constantly grapple with financial strain, compelling management to strike a delicate balance. To maintain timely operations amidst personnel shortages, the workload per individual often increases, placing undue pressure on operation managers responsible for crew management as per legal and regulatory guidelines. To alleviate this issue, we developed an crew management support application specifically for these managers. Given that the application manages sensitive personal and driver information, security considerations are paramount. This paper presents the developed support application and delves into its security implications.

Researching for malware detection using machine learning is becoming active. However, conventional detection techniques do not consider the impact of attacks on machine learning, which has become complicated in recent years. In this research, we focus on data poisoning attack, which is one of the typical attacks on machine learning, and aim to clarify the influence of attacks on malware detection technology. Data poisoning attack is an attack method that intentionally manipulates the predicted result of a learned model by injecting poisoning data into training data, and by applying this, it is possible to embed a backdoor that induces mis-prediction of only specific input data. In this paper, we first propose an attack framework for backdoor embedding that prevents detection of only specific types of malware by data poisoning attack. Next, we will describe a method to generate poisoning data efficiently while avoiding attack detection by solving the optimization problem. Furthermore, we take malware detection technology using logistic regression and show the effectiveness of the our method through evaluation experiments using two datasets.

Hybrid cloud has been considered a viable option to address the unavailability and/or limited resources of an inhouse private cloud as per user's requirements or at runtime. The approach is poised to highly benefit the user in terms of procuring the required resources and/or the time element. With many companies offering different features of public cloud services, even if such service is of the same type, the quest to discover and select the suitable public cloud service provider is of utmost importance. This paper proposed anagent-based support system to discover the most suitable public cloud service provider based on the user's requirements. Agents and ontologies were used to implement the proposed model. Verification test results demonstrates the viability and usefulness of the system.

Sub-ontology extraction provides a solution in dealing with large ontology. As time progresses, new discoveries and new ontology emerges making the ontology data much larger. Updating the sub-extracted ontology becomes a crucial task. Updating extracted sub-ontology can be done by performing the whole extraction process repeatedly from the base ontology. In contrast, our proposed approach is to develop an incremental update mechanism which can minimize the large communication and processing overhead in the former method. In this paper, we construct and describe a grid application service framework for updating extracted sub-ontology using the incremental update mechanism. The service can be accessed through a web portal. Functional verification and analysis provides viability of the framework.

The semantic grid as the uniting concept of semantic web and grid computing, and its ontology technology provide an efficient data retrieval methodology in widely distributed semantic grid resources over the Internet. As the number of semantic grid resources increase, e.g., ontology servers, the amount of data increases and managing job workflows is becoming increasingly complex. This paper proposed a validation framework for sub-ontology extraction workflows in our proposed semantic grid computing environment. We considered two ontology optimization schemes and design its workflow models using Petri Net. The workflow for each model is described and validated. The results justify the feasibilities of our proposed validation framework of the aforementioned models which can be used as building blocks to model large and efficient sub-ontology extraction workflows in a semantic grid.