Feature Selection task is one of the most complicated and actual in the areas of Data Mining and Human Machine Interaction. Many approaches to its solving are based on non-mathematical and presentative hypothesis. New approach to evaluation of medical features information quantity, based on optimized combination of feature selection and feature extraction methods is proposed. This approach allows us to produce optimal reduced number of features with linguistic interpreting of each of them. Hybrid system of feature selection/extraction based on Neural Network-Physician interaction is investigated. This system is numerically simple, can produce feature selection/extraction with any number of factors in online mode using neural network-physician interaction based on Oja’s neurons for online principal component analysis and calculating distance between first principal component and all input features. A series of experiments confirms efficiency of proposed approaches in Medical Data Mining area and allows physicians to have the most informative features without losing their linguistic interpreting.

/pdf/adaptive-human-machine-interaction-approach-for-feature-220o4pjfan.pdf

Adaptive human machine interaction approach for feature selection-extraction task in medical data mining

Bottle Recycling Machine (BRM) plays a vital role in solving the issue of solid waste as used bottles are the major factors for water and land pollution. Here we propose novel design for Brmto collect the used bottles and classify them usingmachine learning algorithm. After classification separate mechanism has been implemented forrecycling of used bottles. The system consist raspberry-PI connected with camera and audio-visual interactive system. For encouraging users, reward is given through printed coupon generated using thermal receipt printer. Since there is no sensor available to detect plastic bottles, this task is done using machine learning algorithm. First step is acquisition of bottle Images and extracted features are given tonovel classifier (machine learning algorithm). The algorithm is developed on with python platform. Once bottles are identified and classified they aresorted using slider crank mechanism as per the type of bottle material. Sorted bottles are recycled using mechanical assembly. The proposed design of BRM provides accurate identification of bottle and effective recycling in low cost.

Development of Bottle Recycling Machine Using Machine Learning Algorithm

Automatic coin recognition and identification systemplays vital role in vending machine, slot machine and in several banking related equipment's. Most of the existing coin recognitions systems are based on physical parameters of the coins whereas image processing methodologies relies on extraction of color, shape and edge features. For recognition and detection of Indian coin we have proposed Deep Learning approach in this paper. Pretrained convolutional neural network i.e. AlexNet is trained by using the features such as textures, colors and shape. The model is trained on more than 1600 images and can classify images into four object categories like one, two, five and ten rupees coins. The trained model is tested on various standard and own recorded datasets consist of rotational, translated and shifted images. The parameters used to calibrate the performance system are recognition accuracy and response time. Obtained results shown the outperformance of proposed methodology over conventional systems.

Deep Learning Based Indian Currency Coin Recognition

War field surveillance system plays vital role in security of every Nation. Major problems related are surveillance at national borders. Manual monitoring is relatively difficult in case of the borders where the area is too big; specifically, during night the majority of the attacks are executed by rivals where the human vision is not capable to identify enemy location. Therefor intelligent system needs to be developed which will automatically identify survival of enemy in less light situation or night. We put forward intelligent war field surveillance system consist of raspberry pi processor interfaced with night vision camera capable of sensing environment, intelligent decision making, commanding capability and performing action on the environment. The Internet of things is used to inform concern authority about enemy status. This system includes night vision camera and raspberry pi module which can transmit videos of the war field sequentially to prevent any hurt and loss to human life. The system will be used as proper machine for the defence sector to decrease the loss of human life and also useful to decrease infiltrations at border regions. It works on the principle of optical flow algorithm for movement detection. The developed algorithm is implemented in real time by motion based moving object detection method.

Surveillance System for Detection of Suspicious Human Activities at War Field

This paper represents the system is based on the identification of human body, object and suspicious activity detection. The survey of videos is important solution for people having priorities in market, buildings, train stations, courts, religious places and airport etc. Video provided as input then it converted into sequence of frames and these frames are used for the detection of object. The contributions for activity observation are proposed. It is challenging task for object tracking and video surveillance and because of illumination changes, quick variations in object appearance, similar non target objects in background and obstacle. The algorithm includes of different steps having video compression, object detection, and object localization. The main advantages of this algorithm are accurately moving object and doubtful activity recognition.

Motion estimation for human activity surveillance

Human machine interaction is an evolving research area which deals with interactions with machines that will be as natural as an interaction between humans. Vision based motion estimation can also be said as the interpretation of motions via mathematical algorithms. This system have applications in domains such as sign language translation, virtual environments, smart surveillance, controlling robots, control of machines, medical systems etc. The task is challenging due to the accuracy, further the items in the background or distinct features of the users may make recognition more difficult. In this survey, we address these challenges. We provide an overview of current advances in the field. Further, we discuss limitations and outline promising directions of research. A brief overview of methodologies implemented by earlier researcher on vision based gesture recognition for human machine interaction is discussed here.

Motion estimation for human-machine interaction

and estimation of human body motion is a challenging issue for real-time human-machine interaction. Real-time processing and accuracy are key requirements during the designing of the system. The task of detecting and estimating human motion is a very important aspect for various high-level applications. However, many methods suffer because of not having enough robust estimation and proper motion detection. This paper presents a novel human motion detection algorithm that uses a background subtraction based segmentation based on moving blob regions. Considering the accuracy, here in this system a single video camera is employed without any auxiliary marking tools. This approach first obtains a background image through the acquisition and enhancement of video sequences. Then, it obtains a motion image which is then subtracted from the background image to detect the motion. Pre-processing is then applied to the difference image before the major blob is identified. We then calculate the angle of the motion that was detected by the difference image to evaluate the motion effectively. This measured angle is then sent to the hardware control through wireless transmission. Based on the range of the angle, the room lights and fan speed is controlled. Multiple experimental results demonstrate the accuracy of this system.

/pdf/vision-based-motion-estimation-for-human-machine-interaction-3u9bjyxxwc.pdf

Prerna D. Uddharwar

Papers

Motion estimation for human-machine interaction

Vision based Motion Estimation for Human Machine Interaction