Shop

Showing 61–72 of 142 results

  • LIDAR-based Object Classification for Autonomous Driving on Urban Roads

    Open Access

    Abstract: Object classification is an important technique for autonomous vehicles to identify surrounding dynamic objects and execute safe path planning. In this paper, a multi-class object classification method is proposed to classify objects around the vehicle into car, pedestrian bicyclist, and background using a LIDAR sensor. The various effective features of each object are computed using 3D point clouds, and Real AdaBoost algorithm is applied for multi-class classification. In addition, class probabilities are calculated and updated in a time series framework for tracking objects. Classification is evaluated using a dataset that includes long-range objects over 50m. The overall accuracy of the clusters for each frame is 92.7% and for tracking objects is 95.5%. Moreover, processing time for object classification is 0.07ms. Thus, this method can be used in real time for autonomous driving on urban roads.

  • Rapid Human Body Detection in Disaster Sites using Image Processing from Unmanned Aerial Vehicle (UAV) Cameras

    Open Access

    Abstract: The development and impact of technology on our everyday lives cannot be compared with the world our ancestors lived in several decades ago. This is described as the world of technology (WoT). But despite all the advancements in technologies, understanding of the mechanisms of nature and the damages caused via natural disasters, such as earthquakes, landslides, and flooding to mention only a few, are still very far away. In the effort of saving lives during natural disasters, such as earthquakes, this study introduces a rapid human body detection technology using image processing from UAV camera. The skin color from a female student is first extracted in RGB then converted to HSV. Next, opening and closing morphological operations are performed eight times each to remove all noise present in the image. Experimental tests were performed both indoor and outdoor, where the female student presented an object close and far to the camera to check the detection capability in both cases. The experiment results show that close or far, the camera can clearly detect both a human body and any part of a human body. The results of the experiment proves the merit of the proposed method.

  • Convolutional Neural Network Based Vehicle Turn Signal Recognition

    Open Access

    Abstract: Automated driving is an emerging technology in which a car performs the tasks of recognition, decision making, and control. Recognizing surrounding vehicles is vital in generating the trajectory of an ego-vehicle. This paper focuses on detecting a turn signal information as one of the driver’s intention for surrounding vehicles. This information helps to predict the driver’s behavior in advance especially as instances of lane change and turns at an intersection. Using their intension, the automated vehicle is able to generate a safety trajectory before the driver’s behavior changes. The proposed method recognizes the turn signal of the target vehicle using a mono-camera. It detects the lighting state using Convolutional Neural Network, and then calculates a flashing frequency using Fast Fourier Transform.

  • An Assistive Robotic Arm for People with Severe Disabilities:Evaluation of Eating Soup

    Open Access

    Abstract: An assistive robotic arm for people with severe disabilities is presented in this paper. Its user interface using eye movements consists of a Web camera, computer, and microcontroller with display unit. Using the robotic arm system, we performed two experiments: (1) transferring water task and (2) eating soup task. It was found from the experimental results that the assistive robotic arm system could stably and appropriately transfer more than 82 % of water and 86 % of soup to the respective positions.

  • Preliminary Assessment for Inshore Fishing UAV (ISFUAV)

    Open Access

    Abstract: The development and entry into service of unmanned air vehicle (UAV) systems has a long, history. Unfortunately, the vision of engineers and scientist is have seldom matched that of administrators, regulators or financiers. The availability of UAV systems has also often depended upon the maturation of the requisite technology. UAV systems are now being operated by several military forces and currently, to a more limited extent, by civilian organizations. Civilan organizations, however, may eventually expand to exceed, in number and diversity, those of the military [1]. UAV are now use in many domains to perform tasks that may cause risk to human life or in the surveillance of the suicide sites to prevent young people in depression to from committing suicide. UAV are also used to collect information to support decision making during crises, in monitoring disasters sites, for assisting rescue teams during the rescue operations and the list goes on. Given the capability of UAV to perform many civilian tasks to contribute to a sustainable society, this paper assesses what is needed to move the UAV to the fishing industry in order to develop the Inshore Fishing Unmanned Aerial vehicle (ISFUAV). The assessment consists of how to combine real fishing materials, their fishing material weight in relation to the ISFUAV, and the system capable of carrying those fishing materials to the fishing area into the sea and depth zone fishing.

  • Verification Experiment for Drone Charging Station Using RTK-GPS

    Open Access

    Abstract: In recent years, Drone’s research has become popular, and there is a need to automate the cycle of takeoff, flight, landing, and charging of Drone. Mainly, the problem remains in automatic battery charging. Therefore, in this research, we will realize Drone’s charging station using RTK-GPS with high accuracy. We verified the landing accuracy by experiment. From the results of the verification, it was found that relative positional error between drone and the charging station can be eliminated by referring to the same reference position. Thus, the possibility of navigating Drone to the charging station can be easily implemented.

  • Optogenetics-based Neuromodulation for the Alleviation of hemi-Parkinsonian Motor Asymmetry in Rat

    Open Access

    Abstract: The development of more effective deep brain stimulation (DBS) paradigms for Parkinson’s disease is limited by the non-specific nature of electrical stimulation. Optogenetics, with its spatial and cell-type specificity, is a potential alternative therapeutic approach. In 6-hydroxydopamine-induced hemi-Parkinsonian rats, we investigated the therapeutic values of optogenetic modulation of the subthalamic nucleus (STN) and the motor cortex. Here we report optogenetic inhibition of principal neurons in the STN significantly improved hemi-Parkinsonian motor asymmetry, measured by amphetamine-induced rotations. We also show preliminary results that revealed therapeutic improvement in motor asymmetry by single-site optogenetic excitation of the motor cortex. Although improvement from optogenetic modulations did not exceed the effects of DBS in the STN, our findings suggest that spatially patterned optogenetic stimulation of the cortex, i.e., more precise manipulation of cortical activity over larger area, should be investigated as a therapeutic approach for Parkinson’s disease.

  • The Role of Neuroimaging in Diagnosis of Neurodegenerative Disease

    Open Access

    Abstract: Imaging the human body is one of the most important aspects of medical science in clinics and research. Due to the increasing spread of diseases related to the nervous system, neuroimaging has grown substantially in the last two decades. In this study, neuroimaging techniques that are used to diagnose neurodegenerative diseases have been expressed. Clinical applications of each neuroimaging method have also been reviewed. Some imaging techniques create structural and anatomical images, and some provide physiological and functional images. Recent advances in neuroimaging have led to the creation of hybrid techniques. In these multimodality methods, structural and functional images are combined. This feature leads to increased accuracy in the diagnosis of neurodegenerative diseases.

  • Controlling 3D Object made of CT data in Medical Training System Using Leap Motion

    Open Access

    Abstract: This paper describes a user interface of 3D (three-dimensional) object converted from 2D (two-dimensional) CT data in DICOM format using Leap Motion device that can be used as a medical training system for medical students and interns. The resultant data can be controlled in a 3D development environment of Unity software. The system consists of desktop computer, the displaying software environment and Leap Motion device. The experimental results show that we can have a desirable control over the rendered object in 360 degrees, and that we can check the details of the object using zooming feature in the system.

  • Multi-label classification of brain tumor mass spectrometry data. In pursuit of tumor boundary detection method.

    Open Access

    Abstract: The mass-spectrometry is the promising tool for the fast characterization of brain biopsy samples as a part of the intraoperative identification of tumor boundary. The spray-from-tissue ambient ionization method is a new instrument for mass-spectrometry analysis of soft tissues without sample preparation. In this contribution, we analyze the performance of multi-label classification techniques in detection of the tumor and necrosis fragments within the sample.

  • Decision Making Using Fuzzy Cognitive Maps in Post-Triage of Non-Critical Elderly Patients

    Open Access

    Abstract: For patients arriving in the Emergency Departments (EDs) of hospitals a key aspect is to classify patients and identify high-risk patients since they have the potential for rapid deterioration during the waiting time. Triage is a widely applied and well-known process of evaluating and categorizing patients’ condition, in EDs. On the other hand, EDs are frequently overcrowded, which makes triage an extremely challenging and demanding process in order to ensure that patients stepping into the ED are given the appropriate medical attention in time. This paper discusses the introduction of a general decision making procedure based on Fuzzy Cognitive Maps so that to create a Medical Decision Support System for Post-Triage decisions. The case of non-emergent and non-urgent elderly patients is examined and the corresponding model is developed.

  • Supervised Learning-based Nuclei Segmentation on Cytology Pleural Effusion Images with Artificial Neural Network

    Open Access

    Abstract: Automated segmentation of cell nuclei is the crucial step towards computer-aided diagnosis system because the morphological features of the cell nuclei are highly associated with the cell abnormality and disease. This paper contributes four main stages required for automatic segmentation of the cell nuclei on cytology pleural effusion images. Initially, the image is preprocessed to enhance the image quality by applying contrast limited adaptive histogram equalization (CLAHE). The segmentation process is relied on a supervised Artificial Neural network (ANN) based pixel classification. Then, the boundaries of the extracted cell nuclei regions are refined by utilizing the morphological operation. Finally, the overlapped or touched nuclei are identified and split by using the marker-controlled watershed method. The proposed method is evaluated with the local dataset containing 35 cytology pleural effusion images. It achieves the performance of 0.95%, 0.86 %, 0.90% and 92% in precision, recall, F-measure and Dice Similarity Coefficient respectively. The average computational time for the entire algorithm took 15 mins per image. To our knowledge, this is the first attempt that utilizes ANN as the segmentation on cytology pleural effusion images.