Sasa Vukosavljev

System Design for Passive Human Detection Using Principal Components of the Signal Strength Space

Radio irregularity phenomenon is often considered as a shortcoming of wireless sensor networks. In this paper, the radio irregularity is regarded as a benefit of wireless networks. The proposed novel method for human presence detection, applied to the monitoring system for residential energy management, utilizes radio irregularity for an efficient human presence detection which increases user awareness and automates the power control. The method monitors 2.4GHz wireless (Zigbee) smart outlets and the communication signals between them to detect changes of the received signal strength indicator (RSSI) and its variations compared to the expected mean values. The signal strength variation is significantly increased due to human presence within the signal propagation path. By applying the algorithm for principal components analysis to the set of RSSI samples obtained from radio communication links within the detection area, it is possible to recognize a human presence. There is no need for additional presence sensors installation, because the proposed method applied to the smart outlets network is quite satisfactory to extend the entire system with the detection capability. Compared to the conventional sensor networks, the presented solution preserves the pervasiveness of smart energy and smart home systems, high level of sensorial intelligence, simplicity and low installation costs.

Mobile robot control using self-learning neural network

The paper describes the concept of the navigation system for a mobile robot. The system is using a navigation algorithm based on self-learning neural network, necessary to form a movement plan for a robot. The algorithm is adapted and implemented to navigate real platform of a mobile robot equipped by two independent wheel drives, encoders and a set of short-range sonars. Navigation algorithm is placed into a PC, which is connected to mobile robot by wireless and wired links. Experiments have shown ability of collision-free navigation of mobile robot in real time.

System and method for passive surveillance in indoor environments based on principal components of the signal strength variation

Efficient wireless sensor nodes have significantly motivated the usage of wireless sensor networks for intrusion detection and surveillance. A passive wireless surveillance network has the ability to detect humans by analyzing only the variations of the signal strength with respect to distance and alignment between nodes. When a human passes through an area covered by radio network, his/her body interferes with radio signals resulting in signal strength variations due to absorption, reflection and diffraction. In this paper, we analyze the signal strength variation induced by human presence, as a reliable method for passive surveillance. The proposed method analyzes principal components from a covariance matrix composed of samples that present signal strength variations gathered from wireless nodes. By using smart wireless outlets and inter-outlets communication signals, the original environment is not visually modified, but a certain level of sensorial intelligence is introduced without additional sensors. Principal component analysis enhances the detection accuracy level and improves the overall robustness of the surveillance method. Compared to conventional sensor networks, the use of smart wireless outlets and signal strength analysis preserves the transparency of the surveillance system and supports high level of sensorial intelligence, retaining low installation costs.

Hands-free voice communication platform integrated with TV

This paper presents a system for full-duplex hands free voice communication integrated with TV technology. The system provides comfort conversation by utilization of microphone array and advanced voice processing algorithms, even with simultaneous TV usage. As communication channel GSM or VoIP can be used.

Mobile robot control using combined neural-fuzzy and neural network

This paper describes the concept of the navigation system for a mobile robot. The system is using a combination of two navigation algorithms: self-learning neural network, necessary to form a movement plan for a robot, and a collision-free control algorithm based on heuristic neuro-fuzzy approach. The basic task of neural network is to generate initial path. Heuristic base of rules for collision free algorithm are limited and does not cover all situations. Main contribution of proposed navigation is related to neural network property to supplements special cases that are not covered by present heuristic rules from the data base. Both algorithms are adapted and implemented to navigate real platform of a mobile robot equipped by two independent wheel drives, encoders and a set of short-range sonars. The combined reactive algorithm (using two control methods) is used in real time for obstacle navigation in robotized system. Navigation algorithms are placed into a PC, which is connected to mobile robot by wireless and wired links. Experiments have shown ability of collision-free navigation of mobile robot in real time.

A Generic Embedded Robot Platform for Real Time Navigation and Telepresence Abilities

This paper presents a generic embedded robot platform concept that meets functional and real time requirements. The described concept allows easy system extension with new components, simple configuration and implementation of advanced features. Design and development of such complex system poses significant challenges and requires knowledge from several scientific fields as: mechanics, electronics, software and computer engineering. Proposal for hardware control units of these robots is based on the modern families of microcontrollers and DSPs coprocessors which are relevant for autonomous mobile application regarding requirements for interfaces, processing power, memory and power consumption. Typical software for robots generally includes control/navigation and communication functions. In the last decade multimedia software technologies also took place in the robotic system architecture to improve robot capabilities. The concept is proposed after analysis of spatial, temporal, and functional requirements. It involves a generic architecture using modular hardware design and software component based approach. The concept is illustrated by typical use case -- wireless/wired controlled robot. Besides basic navigation commands set, it is able to transmit audio and video information. This provides telepresence impression to the remote operator. The presented approach offers a convenient/flexible platform for further development focused on specific areas such as: intelligent navigation, sensor arrays, wireless networking, human machine interaction, audio and video processing.

Jedno rešenje programske podrške za parsiranje i vizuelizaciju signala sadržanih u TTL datoteci

The task is the realization the program for parsing XML files and TTL as well as graphical representation of the signal contained therein. TTL is a log file. Information exchanged in the car on different types of car system such as CAN, FlexRay, LIN, and similar are collected in TTL file. The toolkit parses messages arriving from different interfaces where each interface has a unique message content. Data Logger, the device with support for a wide variety of buses, collects information from the vehicle during the exchange of data between different control units (ECU) of the vehicle. A Data Logger stores data in TTL file. By analyzing the plotted graphs users can detect the correctness of signals and make decision whether it will further do analyze. The goal of developing application is to enable all users, of Data Logger application, graphical representation of recorded signals from vehicles without use of licensed and expensive applications. Also, applications goal is to simplify control of different safety devices in vehicle over graphical representation of their signals.

One solution of the light source based on LED with radio-control provided with Zigbee-compatible microcontroller CC2530

This paper describes one solution of LED based luminaire control. The device is powered by 230V/50Hz AC network using 20W flyback regulator with optimized PFC, which is an advantage over common CLF lamps. Current through 4 strips of LED diodes (red, green, blue and white) is controlled by 4 independent buck regulators using 4 PWM signals from Zigbee-compatible microcontroller CC2530. This way a full control over light intensity and spectral content is achieved, as well as compatibility with existing remote controller from OBLO home automation system.