Mladen Russo

Location Determination in Indoor Environment based on RSS Fingerprinting and Artificial Neural Network

Wireless microsensor networks have been identified as one of the most important technologies for the 21st century. Cheap, smart devices with multiple onboard sensors, networked through wireless links and the Internet and deployed in large numbers, provide unprecedented opportunities for instrumenting and controlling homes, cities, and the environment. One of the crucial issues in wireless sensor networks is position determination. In this work a positioning system based on received signal strength (RSS) and WLAN is presented. In indoor environments, received signal strength is a complex function of distance. In this work artificial neural network is used to establish a relationship between RSS and location. The location determination accuracy of the proposed system has been investigated and promising results have been achieved. Although based on WLAN technology, the same positioning technique can be applied to any wireless mobile device or sensor in a wireless sensor networks.

Adaptive Noise Cancellation Based on Neural Network

There are many noise cancellation applications which require utilization of adaptive filters. An adaptive noise canceller adaptively filters a noise reference input to maximally match and subtract out noise or interference from the primary (signal plus noise) input. In this work we use a simple neural network called Adaline as adaptive filter. Our experiments are based on engine noise cancellation in cars

Fingerprinting based localization in heterogeneous wireless networks

Due to advances in mobile technology, context-aware applications are continuously growing in importance; therefore, the ability of developing accurate and reliable localization system has become a necessity. Since methods based on received signal strength (RSS) fingerprints are today widely adopted and most of mobile devices comprise different wireless access technologies, it is feasible to use fingerprints from heterogeneous wireless networks (HWN) for localization purposes. In this paper we propose a novel approach for localization based on searching the area which best matches the test RSS fingerprint. We evaluated the proposed method in realistic environment in WLAN, GSM and UMTS networks, and compared it with other commonly used approaches. The results showed that our method compares favorably to others, and practically always achieves the lowest localization error. We also extended the proposed system using a model of cooperative positioning by combining the estimates obtained in the heterogeneous wireless network. The obtained results showed that with combined location estimate, significant improvement over any single system was achieved.

Probabilistic Modeling of Harvested GSM Energy and its Application in Extending UHF RFID Tags Reading Range

Newer silicon-based consumer electronics became very popular due to its reduction in size, price, and power consumption. One of its applications today is building low-power devices for ubiquitous sensing. Although sensors are low-power devices, they need some energy source to function properly. One of the major challenges today is to develop systems where sensors do not require external power sources, and could be powered using available ambient energy. To address this power issue one could use energy harvesting concepts. In this paper, we present our probabilistic approach used for modeling the possible amount of Global System for Mobile Communication (GSM) energy that could be harvested, including a demonstration of what power levels could be harvested using GSM rectifying antenna (rectenna). In addition to harvesting approach, we propose an application of its usage in increasing the communication range between Radio Frequency Identification (RFID) reader and battery free passive RFID tags.

Speech recognition over Bluetooth ACL and SCO links: a comparison

Bluetooth is an emerging technology for short-range wireless communication. It is designed to transfer data over asynchronous connectionless (ACL) links and voice over synchronous connection-oriented (SCO) links. SCO packets are sent at regular intervals and are never retransmitted, while ACL packets are retransmitted in case of error. In this paper we have investigated speech recognition performance for voice transferred over ACL and SCO links at various channel qualities. Our experiments have shown that channel quality has severe impact on speech recognition performance for voice earned over SCO. This justifies the use of ACL links for voice transmissions in speech recognition applications.

Biophysical Cochlear Model : Time-Frequency Analysis and Signal Reconstruction

The cochlea transforms incoming sound pressure into vibrations of the basilar membrane which give rise to neural impulses. Although it has been an object of research for several decades, complete understanding of its behavior is far from complete. Many experiments on real cochlea and many mathematical models have been developed in the past decades. In the biophysical cochlear model of Mammano and Nobili [1, 2], both mechanical and hydrodynamical aspects are treated at a level adequate to the complexity of realistic cochlear structures. In this paper, we analyze the time-frequency resolution of this biophysical cochlear model: analysis is first applied to the passive cochlear model and then extended to the active nonlinear model. Further, we propose the method for signal reconstruction from the cochlear time-frequency response. When applied to active cochlear model response, it could result with the signal which human ear actually hears (with some spectral enhancements and noise suppression).

Improved Linearized Combinatorial Model (ILCM) for optimal frame size selection in ALOHA-based RFID systems

Radio Frequency Identification (RFID) technology became the most important tool for identification of items and tracking. Nowadays, the most popular in terms of best price-performance ratio is passive RFID technology, where tags are both powered-up and communicating using the same radio waves transmitted via reader antenna(s).

Wearable Emotion Recognition System based on GSR and PPG Signals

In recent years, many methods and systems for automated recognition of human emotional states were proposed. Most of them are trying to recognize emotions based on physiological signals such as galvanic skin response (GSR), electrocardiogram (ECG), electroencephalogram (EEG), electromyogram (EMG), photoplethysmogram (PPG), respiration, skin temperature etc. Measuring all these signals is quite impractical for real-life use and in this research, we decided to acquire and analyse only GSR and PPG signals because of its suitability for implementation on a simple wearable device that can collect signals from a person without compromising comfort and privacy. For this purpose, we used the lightweight, small and compact Shimmer3 sensor. We developed complete application with database storage to elicit participant»s emotions using pictures from the Geneva affective picture database (GAPED) database. In the post-processing process, we used typical statistical parameters and power spectral density (PSD) as features and support vector machine (SVM) and k-nearest neighbours (KNN) as classifiers. We built single-user and multi-user emotion classification models to compare the results. As expected, we got better average accuracies on a single-user model than on the multi-user model. Our results also show that a single-user based emotion detection model could potentially be used in real-life scenario considering environments conditions.

Wearable technologies for smart environments: A review with emphasis on BCI

In recent years, there has been a growing demand for the development of smart environments to improve quality of life. A major role in this process have wearable devices capable of monitoring and recording psychophysiological measures/signals required for variety of applications including remote health monitoring, physical activity monitoring and general user interaction. This paper surveys the current state of technology, models and requirements of wearable devices with emphasis on Brain Computer Interface (BCI). BCI technology is a rapidly growing scientific field with a number of practical applications providing useful and accurate information and has a promising future. The paper also summarizes the current applications of BCI and presents their limitations and signal-processing algorithms. This area will be the biggest challenge of future research and development process. Other challenges include connectivity, data input, security, design, robustness, low energy consumption and energy harvesting.

Soundscape of an Archaeological Site Recreated with Audio Augmented Reality

This article investigates the use of an audio augmented reality (AAR) system to recreate the soundscape of a medieval archaeological site. The aim of our work was to explore whether it is possible to enhance a tourists archaeological experience, which is often derived from only scarce remains. We developed a smartphone-based AAR system, which uses location and orientation sensors to synthesize the soundscape of a site and plays it to the user via headphones. We recreated the ancient soundscape of a medieval archaeological site in Croatia and tested it in situ on two groups of participants using the soundwalk method. One test group performed the soundwalk while listening to the recreated soundscape using the AAR system, while the second control group did not use the AAR equipment. We measured the experiences of the participants using two methods: the standard soundwalk questionnaire and affective computing equipment for detecting the emotional state of participants. The results of both test methods show that participants who were listening to the ancient soundscape using our AAR system experienced higher arousal than those visiting the site without AAR.