Kyutacar : Kyushu Institute of Technology Academic Repository
Not a member yet
9746 research outputs found
Sort by
Human Motion Recognition from Multiple Directions and Its Gait Cycles Analysis
Get PDFIt is crucial for individuals to keep walking and stay healthy to prevent receiving nursing care. This paper proposes a method of recognizing walk motions and analyzing the gait cycle of a human focusing on his/her posture. We use 43 structural features defined from human joint coordinates obtained using OpenPose and 18 figural features from human domain images and their difference images. The feature vector containing these 61 features is used for the recognition of walk motion by Random Forest. In the experiment, we applied the method to recognizing six types of motions and analyzed the walk gait cycles of five persons, and obtained satisfactory results.conference pape
A Practical Approach of Access Points Installation for Campus WiFi Expansion under the Pandemic
Get PDF九州工業大学では2022年度の後半に，COVID-19の影響によってネットワーク機材の入手性が著しく低下していたなか，工学部が設置された戸畑キャンパスに97台のAP（Access Point）の導入と，114箇所の配線工事を行った．APは2023年2月末と3月中旬の2回に分かれて納品され，かつ配線工事は3月前半から開始であったため，ごく短い期間でAPのキッティングを行い，約2週間かけて配線工事およびAP取付を行った．本稿ではAP設置箇所の選考と現地調査，現地調査に基づく設置箇所の確定，APやPoE Switchの機材選定と実際の手配，およびAPをキッティングする際に工夫した点について報告する．Kyushu Institute of Technology deployed approximately 100 wireless LAN APs (Access Points) at the end of Fiscal Year 2022, while the availability of network equipment was significantly reduced due to COVID-19. In this paper, we describe the selection and field survey of AP installation sites, the determination of installation sites based on the field survey, the arrangement of APs and PoE switches, and a practical approach for access points installation.journal articl
Time evolution of the inner structure of antimony phosphate nanosheet suspension developing structural colouration
Get PDFStructural colouration observed in antimony phosphate nanosheet suspensions has been known for two decades, but the stability of their inner structures has not been a topic in colloidal nanosheet systems. In this study, we investigate the time evolution of structures in suspension using UV-visible spectrometry and small-angle X-ray scattering. Here, we report that antimony phosphate nanosheet systems re-organise their inner structures, especially at lower concentrations (isotropic or biphasic region), and that the basal spacing decreases with time after sample preparation, although the evolution speed depends on the sample concentration. The stability of the inner structure of the suspension is essential for their application as structural colour materials in sensors and colourants.journal articl
MLm5C: A high-precision human RNA 5-methylcytosine sites predictor based on a combination of hybrid machine learning models
Get PDFRNA modification serves as a pivotal component in numerous biological processes. Among the prevalent modifications, 5-methylcytosine (m5C) significantly influences mRNA export, translation efficiency and cell differentiation and are also associated with human diseases, including Alzheimer’s disease, autoimmune disease, cancer, and cardiovascular diseases. Identification of m5C is critically responsible for understanding the RNA modification mechanisms and the epigenetic regulation of associated diseases. However, the large-scale experimental identification of m5C present significant challenges due to labor intensity and time requirements. Several computational tools, using machine learning, have been developed to supplement experimental methods, but identifying these sites lack accuracy and efficiency. In this study, we introduce a new predictor, MLm5C, for precise prediction of m5C sites using sequence data. Briefly, we evaluated eleven RNA sequence-derived features with four basic machine learning algorithms to generate baseline models. From these 44 models, we ranked them based on their performance and subsequently stacked the Top 20 baseline models as the best model, named MLm5C. The MLm5C outperformed the-state-of-the-art predictors. Notably, the optimization of the sequence length surrounding the modification sites significantly improved the prediction performance. MLm5C is an invaluable tool in accelerating the detection of m5C sites within the human genome, thereby facilitating in the characterization of their roles in post-transcriptional regulation.journal articl
Performance Evaluation of Traffic Steering Methods for QoS Improvement in case of Network Failures in Beyond 5G Networks
Get PDFMobile communication networks are expanding. However, when natural disasters happen and communication equipment is damaged, service disruptions can occur and many people cannot use the network. When such disasters happen, it is possible to use long-distance wireless networks such as Low Power Wide Area (LPWA) networks or satellite communication networks as alternative routes. This study focuses on the network between the Beyond 5G core network and the remote host and proposes a resilient network that uses the open RAN (O-RAN) architecture to utilize available communication networks during failures. Additionally, we propose a traffic steering method based on the types of user devices to effectively use available alternative routes and alleviate QoS degradation for users. This paper evaluates the effectiveness of the proposed system through simulations. The simulation results showed that the proposed methods increase the satisfaction rate of flows’ requirements.journal articl
R&D of the EM Calorimeter Energy Calibration with Machine Learning based on the low-level features of the Cluster
Get PDFWe have developed an energy calibration method using machine learning for the ILC electromagnetic (EM) calorimeter (ECAL), a sampling calorimeter consisting of Silicon-Tungsten layers. In this method, we use a deep neural network (DNN) for a regression to determine the energy of incident EM particles, improving the energy calibration resolution of the ECAL. The DNN architecture takes cluster hit data as low-level features of the cluster. In this paper, we report the status of our R&D and present results on energy calibration accuracy.journal articl
Design of 3U LEOPARD CubeSat with Deployable Solar Panels from Integration to Structural and Vibration Analysis
Get PDFLEOPARD (Light intensity Experiment with On-orbit Positioning and satellite Ranging Demonstration) is a 3-unit (3U) research CubeSat with various mission objectives such as light-scattering observation over the horizon with a multispectral camera, onboard processing of Earth-origin one-way radio ranging signal (OPERA), single event latch-up (SEL) detection, solar panel deployment demonstration with shape memory alloy (SMA), and measurement of magnetic field independent components of stray and natural fields. The solar panel deployment mechanism utilizes shape memory alloy with a heater to ensure controlled panel deployment. In this paper, the structural design of the LEOPARD CubeSat is presented in addition to the assembly and integration procedures. Furthermore, structural analysis is presented from modal analysis to static load analysis, and the simulation of stress distributions and validation of structural integrity have been performed with finite element analysis. Vibration testing is also conducted to evaluate the system level response to mechanical excitations during launch, ensuring robustness against dynamic loads. LEOPARD used a slot-type design for subsystem integration that has been used in our previous satellites, and the novelty of the structure design comes from the deployment mechanism and method. Finally, the LEOPARD flight model is under testing, and the operation is expected to begin in the second half of 2025.conference pape
Text-Image Transformation by Text Painterly Analysis and Generative AI
Get PDF俳句・短歌などの短文テキストを対象として，そのテキストがどの程度事物や事象を具体的・視覚的に表現しているか，すなわち，テキストの絵画性（painterly）の分析を行った．テキストの絵画性は，テキストの具体性（concreteness）と視覚性（visibility）からなる．そこで，まず，テキストに出現する語の具体度に基づくテキストの絵画性分析を行った．さらに，画像生成 AI を用いてテキスト-画像変換を行って画像の自動生成を行った．自動生成された画像の妥当性分析をテキストの絵画性を用いて行った．We analyzed the “painterly” of text such as Haiku and Tanka. The “text painterly” means the degree of text concreteness and text visibility (how much the text can give rise to images), and the text concreteness was computed by word concreteness. Then, we applied text-image transformation by generative AI to highly painterly text.journal articl