High Accuracy WiFi-Based Human Activity Classification System with Time-Frequency Diagram CNN Method for Different Places.

Older people are very likely to fall, which is a significant threat to the health. However, falls are preventable and are not necessarily an inevitable part of aging. Many different fall detection systems have been developed to help people avoid falling. However, traditional systems based on wearable devices or image recognition-based have many disadvantages, such as user-unfriendly, privacy issues. Recently, WiFi-based fall detection systems try to solve the above problems. However, there is a common problem of reduced accuracy. Since the system is trained at the original signal collecting/training place, however, the application is at a different place. The proposed solution only extracts the features of the changed signal, which is caused by a specific human action. To implement this, we used Channel State Information (CSI) to train Convolutional Neural Networks (CNNs) and further classify the action. We have designed a prototype to test the performance of our proposed method. Our simulation results show an average accuracy of same place and different place is 93.2% and 90.3%, respectively.

A Novel Synchronous MAC Protocol for Wireless Sensor Networks with Performance Analysis.

Synchronous medium access control (MAC) protocols are highly essential for wireless sensor networks (WSN) to support transmissions with energy saving, quality services, and throughput in industrial, commercial and healthcare applications. In this paper, a synchronous channel access mechanism is designed, where sensors can reserve the contention free data transmission slots in different available channels. To reduce the delay of data transmission among the nodes in the mesh topology, a linear programming problem (LPP) model is designed to select suitable relay nodes. Moreover, the performance of the proposed MAC is analyzed and our models are validated with simulation and analytical results. The results show that our proposed MAC protocol outperforms the IEEE 802.15.4e MAC mechanism in terms of throughput, reliability, delay, energy, packet drop rate and transmission success rate.

Online Distributed User Association for Heterogeneous Radio Access Network.

Future-generation radio access networks (RAN) are projected to fulfill the diverse requirements of user equipment (UE) by adopting a heterogeneous network (HetNet) environment. Necessary integration of different radio access technologies (RAT), such as 2G, 3G, 4G, wireless local area network (WLAN), and visible light communication (VLC) is inevitable. Moreover, UEs equipped with diverse requirements will be capable of accessing some or all the RATs. The complex HetNet environment with diverse requirements of UEs will present many challenges. The HetNet is likely to suffer severely from load imbalance among the base stations (BSs) from inheriting the traditional user association scheme such as max-SINR (signal-to-interference-plus-noise ratio)/max-RSSI (received signal strength indicator), unless some sophisticated schemes are invented. In this paper, a novel scheme is devised for a joint-user association for load balancing, where BSs are densely deployed and UEs typically have a certain degree of mobility. Unlike most of the present works, a dynamic network is considered where the position and channel condition of the UEs are not fixed. We develop two complex and distributed association schemes based on probability and d-choices, while carefully considering both loads of the BSs and SINR experienced by the UEs. Numerical results validate the efficiency of the proposed schemes by showing a received data-rate fairness among UEs and an improvement in the UE's minimum received data rate.

Smart Interactive Education System Based on Wearable Devices.

Due to the popularity of smart devices, traditional one-way teaching methods might not deeply attract school students' attention, especially for the junior high school students, elementary school students, or even younger students, which is a critical issue for educators. Therefore, we develop an intelligent interactive education system, which leverages wearable devices (smart watches) to accurately capture hand gestures of school students and respond instantly to teachers so as to increase the interaction and attraction of school students in class. In addition, through multiple physical information of school students from the smart watch, it can find out the crux points of the learning process according to the deep data analysis. In this way, it can provide teachers to make instant adjustments and suggest school students to achieve multi-learning and innovative thinking. The system is mainly composed of three components: (1) smart interactive watch; (2) teacher-side smart application (App); and (3) cloud-based analysis system. Specifically, the smart interactive watch is responsible for detecting the physical information and interaction results of school students, and then giving feedback to the teachers. The teacher-side app will provide real-time learning suggestions to adjust the teaching pace to avoid learning disability. The cloud-based analysis system provides intelligent learning advices, academic performance prediction and anomaly learning detection. Through field trials, our system has been verified that can potentially enhance teaching and learning processes for both educators and school students.

A Novel IEEE 802.15.4e DSME MAC for Wireless Sensor Networks.

IEEE 802.15.4e standard proposes Deterministic and Synchronous Multichannel Extension (DSME) mode for wireless sensor networks (WSNs) to support industrial, commercial and health care applications. In this paper, a new channel access scheme and beacon scheduling schemes are designed for the IEEE 802.15.4e enabled WSNs in star topology to reduce the network discovery time and energy consumption. In addition, a new dynamic guaranteed retransmission slot allocation scheme is designed for devices with the failure Guaranteed Time Slot (GTS) transmission to reduce the retransmission delay. To evaluate our schemes, analytical models are designed to analyze the performance of WSNs in terms of reliability, delay, throughput and energy consumption. Our schemes are validated with simulation and analytical results and are observed that simulation results well match with the analytical one. The evaluated results of our designed schemes can improve the reliability, throughput, delay, and energy consumptions significantly.

Design and Analysis of a Low Latency Deterministic Network MAC for Wireless Sensor Networks.

The IEEE 802.15.4e standard has four different superframe structures for different applications. Use of a low latency deterministic network (LLDN) superframe for the wireless sensor network is one of them, which can operate in a star topology. In this paper, a new channel access mechanism for IEEE 802.15.4e-based LLDN shared slots is proposed, and analytical models are designed based on this channel access mechanism. A prediction model is designed to estimate the possible number of retransmission slots based on the number of failed transmissions. Performance analysis in terms of data transmission reliability, delay, throughput and energy consumption are provided based on our proposed designs. Our designs are validated for simulation and analytical results, and it is observed that the simulation results well match with the analytical ones. Besides, our designs are compared with the IEEE 802.15.4 MAC mechanism, and it is shown that ours outperforms in terms of throughput, energy consumption, delay and reliability.

A Reliable Data Transmission Model for IEEE 802.15.4e Enabled Wireless Sensor Network under WiFi Interference.

The IEEE 802.15.4e standard proposes Medium Access Control (MAC) to support collision-free wireless channel access mechanisms for industrial, commercial and healthcare applications. However, unnecessary wastage of energy and bandwidth consumption occur due to inefficient backoff management and collisions. In this paper, a new channel access mechanism is designed for the buffer constraint sensor devices to reduce the packet drop rate, energy consumption and collisions. In order to avoid collision due to the hidden terminal problem, a new frame structure is designed for the data transmission. A new superframe structure is proposed to mitigate the problems due to WiFi and ZigBee interference. A modified superframe structure with a new retransmission opportunity for failure devices is proposed to reduce the collisions and retransmission delay with high reliability. Performance evaluation and validation of our scheme indicate that the packet drop rate, throughput, reliability, energy consumption and average delay of the nodes can be improved significantly.

An Efficient Distributed Coverage Hole Detection Protocol for Wireless Sensor Networks.

In wireless sensor networks (WSNs), certain areas of the monitoring region may have coverage holes and serious coverage overlapping due to the random deployment of sensors. The failure of electronic components, software bugs and destructive agents could lead to the random death of the nodes. Sensors may be dead due to exhaustion of battery power, which may cause the network to be uncovered and disconnected. Based on the deployment nature of the nodes in remote or hostile environments, such as a battlefield or desert, it is impossible to recharge or replace the battery. However, the data gathered by the sensors are highly essential for the analysis, and therefore, the collaborative detection of coverage holes has strategic importance in WSNs. In this paper, distributed coverage hole detection algorithms are designed, where nodes can collaborate to detect the coverage holes autonomously. The performance evaluation of our protocols suggests that our protocols outperform in terms of hole detection time, limited power consumption and control packet overhead to detect holes as compared to other similar protocols.

SVANET: A smart vehicular ad hoc network for efficient data transmission with wireless sensors.

Wireless sensors can sense any event, such as accidents, as well as icy roads, and can forward the rescue/warning messages through intermediate vehicles for any necessary help. In this paper, we propose a smart vehicular ad hoc network (SVANET) architecture that uses wireless sensors to detect events and vehicles to transmit the safety and non-safety messages efficiently by using different service channels and one control channel with different priorities. We have developed a data transmission protocol for the vehicles in the highway, in which data can be forwarded with the help of vehicles if they are connected with each other or data can be forwarded with the help of nearby wireless sensors. Our data transmission protocol is designed to increase the driving safety, to prevent accidents and to utilize channels efficiently by adjusting the control and service channel time intervals dynamically. Besides, our protocol can transmit information to vehicles in advance, so that drivers can decide an alternate route in case of traffic congestion. For various data sharing, we design a method that can select a few leader nodes among vehicles running along a highway to broadcast data efficiently. Simulation results show that our protocol can outperform the existing standard in terms of the end to end packet delivery ratio and latency.

Novel Quantitative Analysis Using Optical Imaging (VELscope) and Spectroscopy (Raman) Techniques for Oral Cancer Detection.

In this study, we developed a novel quantitative analysis method to enhance the detection capability for oral cancer screening. We combined two different optical techniques, a light-based detection technique (visually enhanced lesion scope) and a vibrational spectroscopic technique (Raman spectroscopy). Materials and methods: Thirty-five oral cancer patients who went through surgery were enrolled. Thirty-five cancer lesions and thirty-five control samples with normal oral mucosa (adjacent to the cancer lesion) were analyzed. Thirty-five autofluorescence images and 70 Raman spectra were taken from 35 cancer and 35 control group cryopreserved samples. The normalized intensity and heterogeneity of the 70 regions of interest (ROIs) were calculated along with 70 averaged Raman spectra. Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) were used with principal component analysis (PCA) to differentiate the cancer and control groups (normal). The classifications rates were validated using two different validation methods, leave-one-out cross-validation (LOOCV) and k-fold cross-validation. Results: The cryopreserved normal and tumor tissues were differentiated using the PCA-LDA and PCA-QDA models. The PCA-LDA of Raman spectroscopy (RS) had 82.9% accuracy, 80% sensitivity, and 85.7% specificity, while ROIs on the autofluorescence images were differentiated with 90% accuracy, 100% sensitivity, and 80% specificity. The combination of two optical techniques differentiated cancer and normal group with 97.14% accuracy, 100% sensitivity, and 94.3% specificity. Conclusion: In this study, we combined the data of two different optical techniques. Furthermore, PCA-LDA and PCA-QDA quantitative analysis models were used to differentiate tumor and normal groups, creating a complementary pathway for efficient tumor diagnosis. The error rates of RS and VELcope analysis were 17.10% and 10%, respectively, which was reduced to 3% when the two optical techniques were combined.

Raman Spectroscopy Analysis for Optical Diagnosis of Oral Cancer Detection.

Raman spectroscopy (RS) is widely used as a non-invasive technique in screening for the diagnosis of oral cancer. The potential of this optical technique for several biomedical applications has been proved. This work studies the efficacy of RS in detecting oral cancer using sub-site-wise differentiation. A total of 80 samples (44 tumor and 36 normal) were cryopreserved from three different sub-sites: The tongue, the buccal mucosa, and the gingiva of the oral mucosa during surgery. Linear discriminant analysis (LDA) and quadratic discriminant analysis (QDA) were used with principal component analysis (PCA) to classify the samples and the classifications were validated by leave-one-out-cross-validation (LOOCV) and k-fold cross-validation methods. The normal and tumor tissues were differentiated under the PCA-LDA model with an accuracy of 81.25% (sensitivity: 77.27%, specificity: 86.11%). The PCA-QDA classifier model differentiated these tissues with an accuracy of 87.5% (sensitivity: 90.90%, specificity: 83.33%). The PCA-QDA classifier model outperformed the PCA-LDA-based classifier. The model studies revealed that protein, amino acid, and beta-carotene variations are the main biomolecular difference markers for detecting oral cancer.

A novel approach for discovering condition-specific correlations of gene expressions within biological pathways by using cloud computing technology.

Microarrays are widely used to assess gene expressions. Most microarray studies focus primarily on identifying differential gene expressions between conditions (e.g., cancer versus normal cells), for discovering the major factors that cause diseases. Because previous studies have not identified the correlations of differential gene expression between conditions, crucial but abnormal regulations that cause diseases might have been disregarded. This paper proposes an approach for discovering the condition-specific correlations of gene expressions within biological pathways. Because analyzing gene expression correlations is time consuming, an Apache Hadoop cloud computing platform was implemented. Three microarray data sets of breast cancer were collected from the Gene Expression Omnibus, and pathway information from the Kyoto Encyclopedia of Genes and Genomes was applied for discovering meaningful biological correlations. The results showed that adopting the Hadoop platform considerably decreased the computation time. Several correlations of differential gene expressions were discovered between the relapse and nonrelapse breast cancer samples, and most of them were involved in cancer regulation and cancer-related pathways. The results showed that breast cancer recurrence might be highly associated with the abnormal regulations of these gene pairs, rather than with their individual expression levels. The proposed method was computationally efficient and reliable, and stable results were obtained when different data sets were used. The proposed method is effective in identifying meaningful biological regulation patterns between conditions.