Search results

The decline of the motoric and cognitive functions of the elderly and the high risk of changes in their vital signs lead to some disabilities that inconvenience them. This paper aims to assist the elderly in their daily lives through personalized and seamless technologies.

The authors developed a personalized adaptive system for elderly care in a smart home using a fuzzy inference system (FIS), which consists of a predictive positioning system, reflexive alert system and adaptive conditioning system. Reflexive sensing is obtained from a body sensor and environmental sensor networks. Three methods comprising the FIS generation algorithm – fuzzy subtractive clustering (FSC), grid partitioning and fuzzy c-means clustering (FCM) – were compared to obtain the best prediction accuracy.

The results of the experiment showed that FSC produced the best F₁-score (96 per cent positioning accuracy, 94 per cent reflexive alert accuracy, 96 per cent air conditioning accuracy and 95 per cent lighting conditioning accuracy), whereas others failed to predict some classes and had lower validation accuracy results. Therefore, it is concluded that FSC is the best FIS generation method for our proposed system.

Personalized and seamless technologies for elderly implies life-share awareness, stakeholder awareness and community awareness.

This paper presents a model of personalized adaptive system based on their preferences and medical reference, which consists of a predictive positioning system, reflexive alert system and adaptive conditioning system.

Prediction accuracies are usually affected by the techniques and devices used as well as the algorithms applied. This work aims to attempt to further devise a better positioning accuracy based on location fingerprinting taking advantage of two important mobile fingerprints, namely signal strength (SS) and signal quality (SQ) and subsequently building a model based on extreme learning machine (ELM), a new learning algorithm for single‐hidden‐layer neural networks.

Prediction approach to location determination based on historical data has attracted a lot of attention in recent studies, the reason being that it offers the convenience of using previously accumulated location data to subsequently determine locations using predictive algorithms. There have been various approaches to location positioning to further improve mobile user location determination accuracy. This work examines the location determination techniques by attempting to determine the location of mobile users by taking advantage of SS and SQ history data and modeling the locations using the ELM algorithm. The empirical results show that the proposed model based on the ELM algorithm noticeably outperforms k‐Nearest Neighbor approaches.

WiFi's SS contributes more in accuracy to the prediction of user location than WiFi's SQ. Moreover, the new framework based on ELM has been compared with the k‐Nearest Neighbor and the results have shown that the proposed model based on the extreme learning algorithm outperforms the k‐Nearest Neighbor approach.

A new computational intelligence modeling scheme, based on the ELM has been investigated, developed and implemented, as an efficient and more accurate predictive solution for determining position of mobile users based on location fingerprint data (SS and SQ).

The impact of mitigating flood occurrence in the rural and urban areas has become crucial as it has affected government policies for countries that are prone to flood disaster. Efforts and funds have been put up to a higher level of capabilities to ensure that coping and managing flood disaster could be resolved. Several initiatives made in managing flood are: effectively monitoring the potential at-risk inundated area, improving the river water irrigation and drainage and undertaking the environmental pollution. This chapter basically focusses more on the improvement of flood monitoring system device at the potential flood area. The approach of ubiquitous mobile SCADA offers a low-cost, portable, and small in size flood monitoring system device with easily accessible data. An easy web monitoring of environment surrounding anywhere and at any time offers a real-time data updated with a very minimum delay of each and every environment data required. There are several sensors like ultrasonic, sound, temperature and humidity, water drop and vibration sensors are equipped together with one small monitoring system platform. The alert of water level condition is notified through a beeping buzzer and light LED notation of various colors of green, yellow and red, which notify any increase of water exceeded. The platform is powered by a rechargeable battery that allows the platform to be mobile and portable. Hence, flood monitoring system platform promotes a low-cost, easy-to-handle and ubiquitous data updated device for a better monitoring system platform.