Activity recognition plays an essential role in bridging the gap between low-level sensor data and high-level applications ambient-assisted living systems. With aim to obtain satisfactory rate adapt various application scenarios, a variety of sensors have been exploited, among which, smartphone-embedded inertial are widely applied due its convenience, low cost, intrusiveness. In this paper, we explore power triaxial accelerometer gyroscope built-in smartphone recognizing human physical...

Data collection is one of the paramount concerns in wireless sensor networks. Many data algorithms have been proposed for collecting particular monitoring regions. However, efficiency paths such can be improved. This paper proposes an energy-aware path construction (EAPC) algorithm, which selects appropriate set points, constructs a path, and collects from points burdened with data. EAPC intended to prolong network lifetime, it accounts cost its current point next forwarding load each node....

Phase shifting profilometry (PSP) and Fourier transform (FTP) are two well-known fringe analysis methods for 3D sensing. PSP offers high accuracy but requires multiple images; FTP uses a single image is limited in its accuracy. In this paper, we propose novel Fourier-assisted phase (FAPS) method accurate dynamic Our key observation that the motion vulnerability of multi-shot can be overcome through single-shot FTP, while preserved. Moreover, to solve ambiguity complex scenes without...

Among various calamities, conflagrations stand out as one of the most-prevalent and -menacing adversities, posing significant perils to public safety societal progress. Traditional fire-detection systems primarily rely on sensor-based detection techniques, which have inherent limitations in accurately promptly detecting fires, especially complex environments. In recent years, with advancement computer vision technology, video-oriented fire owing their non-contact sensing, adaptability...

Among multiple fault-tolerant strategies, resubmission, and replication are fundamental widely recognized in distributed computing systems. In recent years, many algorithms based on or resubmission have been proposed. However, few of them consider these two techniques together, especially Cloud this article, we propose a Hybrid Fault-Tolerant Scheduling Algorithm (HFTSA) for independent tasks with deadlines by integrating the above virtualized During task scheduling process, HFTSA selects...

The power of end-to-end deep learning techniques to automatically learn latent high-level features from raw signals has been demonstrated in numerous application fields, however, few studies systematically investigate how properly encode the time-series firings binary environment sensors that typically work an event-triggering scheme and have irregular sampling rates for in-home human activity recognition. To this end, we here propose two different methods process streaming sensor readings...

Pervasive computing greatly advances the automatic recognition and understanding of human activities effectively bridges gap between low-level sensor signals high-level human-centric applications. The inherent complexity behavior, however, inevitably poses a huge challenge to design robust activity recognizer, especially in classifying similar activities. In this study, we present hierarchical framework, named HierHAR, that infers on-going multi-stage process for better distinguishing...

Advances in wireless sensor networks and increasing Internet-of-Things devices give great opportunities for smart homecare of the elderly. Smart has been a promising issue received much attention recently. Irregularity detection is one most important issues assessing health condition However, researches focused on explicit irregularity detections which are usually based drastic changes data, such as falling. Existing mechanisms detecting implicit rely subjective assessment behaviors'...

Energy recharging has received much attention in recent years. Several mechanisms were proposed for achieving perpetual lifetime of a given Wireless Sensor Network (WSN). However, most them require mobile recharger to visit each sensor and then perform the task, which increases length path. Another common weakness these works is requirement stop at location sensor. As result, it impossible move with constant speed, leading inefficient movement. To improve efficiency, this paper takes...

Data collection problems have received much attention in recent years. Many data algorithms that constructed a path and adopted one or more mobile sinks to collect along the paths been proposed wireless sensor networks (WSNs). However, efficiency of established still can be improved. This paper proposes cooperative algorithm (CDCA), which aims prolong network lifetime given WSNs. The CDCA initially partitions n nodes into k groups assigns each sink acting as local generated by sensors group....

For the up-and-coming computing models like as cloud computing, service is standard package for meeting all kinds of consumers' requirements. Web Services are concrete implement service. When users request and consume Services, services' reputations will play a vital role in users' selection. A gradually adjusting reputation evaluation method proposed based on eliminating collusive behaviors consumers step by step, reputation-aware model selection designed. In order to adjust reputations,...

Coverage is an important issue that has been widely discussed in wireless sensor networks (WSNs). However, it still a big challenge to achieve both purposes of full coverage and energy balance. This paper considers the area problem for WSN which each variable sensing radius. To prolong network lifetime, weighted Voronoi diagram (WVD) proposed as tool determining responsible region according remaining distributed manner. The mechanism, called radius adaptation (SRA), mainly consists three...

Behavior identification plays an important role in supporting homecare for the elderly living alone. In literature, plenty of algorithms have been designed to identify behaviors by learning features or extracting patterns from sensor data. However, most them adopted probabilistic models supervised based on labeled This paper proposes a behavior algorithm (BIA) using unsupervised unlabeled data alone smart home. presents observation elder with three features: Event Order, Time Length...

In wireless sensor networks, sensors typically aim to transmit their own readings the sink node. Constructing an efficient data collection tree is very important since it can determine lifetime of given WSNs. literature, may studies have investigated this issue and proposed algorithms for mobile visit each such that be directly WSN. However, visiting time consuming which results in long path pass through sensor. Consequently, period between consecutive two visits same long, leading situation...

The irregularity detection of daily behaviors for the elderly is an important issue in homecare. Plenty mechanisms have been developed to detect health condition based on explicit several biomedical parameters or some specific behaviors. However, few research works focus detecting implicit involving combination diverse behaviors, which can assess cognitive and physical wellbeing elders but cannot be directly identified sensor data. This paper proposes Implicit IRregularity Detection (IIRD)...

Abstract Purpose: We aim to develop a back-propagation artificial neural network (BP-ANN) improved by priori knowledge and compare its efficacy with other methods in early diabetic retinopathy (DR) detection. Methods: A total of 240 fundus images, composed 120 early-stage DR normal were obtained the same 45° field view camera, macula at center, as cohort for further training. All retinal images processed, features such blood vessel width tortuosity semi-automatically extracted. An BP-ANN was...

Conventional Gaussian mixture model (GMM) Speech Bandwidth Extension (BWE) methods often suffer from the overly smoothed problem. Thus, a method of BWE based on cluster process and GMM whose parameters are determined by expectation-Maximization (EM) is proposed. Firstly, used to low frequency high parameters, then for each established. Later on, transformed according learned mapping function corresponding GMM. Self-organization Feature Mapping (SOFM) Vector Quantization (VQ) applied as...

The Ordovician-Silurian Wufeng and Longmaxi Shale in the Sichuan Basin were studied to understand genesis diagenetic evolution of carbonate minerals their effects on reservoir quality. results geochemical petrological analyses show that calcite grains have a negative Ce anomaly indicating they formed oxidizing environment seawater. high mineral contents margin basin indicate cores dolomite appear largely be detrital origin. rhombic rims concretions with δ13C -15.46‰ enrichment middle rare...

Activity recognition plays an important role in smart homes for aged-care. In this paper, we formulate the problem of activity and propose a new method based on spatial-temporal constraints to carry out recognition, which consists five phases: initialisation, segmentation, sensor data representation, exploration as well identification. Besides, analyse time complexity space our approach theory. To evaluate approach, carried experiments real dataset from Wireless Mobile Network Laboratory,...