Lightweight Transformer Model for Mobile Application Classification.

Recently, realistic services like virtual reality and augmented reality have gained popularity. These realistic services require deterministic transmission with end-to-end low latency and high reliability for practical applications. However, for these real-time services to be deterministic, the network core should provide the requisite level of network. To deliver differentiated services to each real-time service, network service providers can classify applications based on traffic. However, due to the presence of personal information in headers, application classification based on encrypted application data is necessary. Initially, we collected application traffic from four well-known applications and preprocessed this data to extract encrypted application data and convert it into model input. We proposed a lightweight transformer model consisting of an encoder, a global average pooling layer, and a dense layer to categorize applications based on the encrypted payload in a packet. To enhance the performance of the proposed model, we determined hyperparameters using several performance evaluations. We evaluated performance with 1D-CNN and ET-BERT. The proposed transformer model demonstrated good performance in the performance evaluation, with a classification accuracy and F1 score of 96% and 95%, respectively. The time complexity of the proposed transformer model was higher than that of 1D-CNN but performed better in application classification. The proposed transformer model had lower time complexity and higher classification performance than ET-BERT.

Cyber-WISE: A Cyber-Physical Deep Wireless Indoor Positioning System and Digital Twin Approach.

In recent decades, there have been significant research efforts focusing on wireless indoor localization systems, with fingerprinting techniques based on received signal strength leading the way. The majority of the suggested approaches require challenging and laborious Wi-Fi site surveys to construct a radio map, which is then utilized to match radio signatures with particular locations. In this paper, a novel next-generation cyber-physical wireless indoor positioning system is presented that addresses the challenges of fingerprinting techniques associated with data collection. The proposed approach not only facilitates an interactive digital representation that fosters informed decision-making through a digital twin interface but also ensures adaptability to new scenarios, scalability, and suitability for large environments and evolving conditions during the process of constructing the radio map. Additionally, it reduces the labor cost and laborious data collection process while helping to increase the efficiency of fingerprint-based positioning methods through accurate ground-truth data collection. This is also convenient for working in remote environments to improve human safety in locations where human access is limited or hazardous and to address issues related to radio map obsolescence. The feasibility of the cyber-physical system design is successfully verified and evaluated with real-world experiments in which a ground robot is utilized to obtain a radio map autonomously in real-time in a challenging environment through an informed decision process. With the proposed setup, the results demonstrate the success of RSSI-based indoor positioning using deep learning models, including MLP, LSTM Model 1, and LSTM Model 2, achieving an average localization error of ≤2.16 m in individual areas. Specifically, LSTM Model 2 achieves an average localization error as low as 1.55 m and 1.97 m with 83.33% and 81.05% of the errors within 2 m for individual and combined areas, respectively. These outcomes demonstrate that the proposed cyber-physical wireless indoor positioning approach, which is based on the application of dynamic Wi-Fi RSS surveying through human feedback using autonomous mobile robots, effectively leverages the precision of deep learning models, resulting in localization performance comparable to the literature. Furthermore, they highlight its potential for suitability for deployment in real-world scenarios and practical applicability.

Design and Implementation of a Video-Frame Localization System for a Drifting Camera-Based Sewer Inspection System.

To reduce the cost of inspecting old sewer pipes, we have been developing a low-cost sewer inspection system that uses drifting wireless cameras to record videos of the interior of a sewer pipe while drifting. The video's data are transmitted to access points placed in utility holes and further transmitted to a video server where each video frame is linked to its capturing position so that users can identify the damaged areas. However, in small-diameter sewer pipes, locating drifting nodes over the full extent of the pipeline using Wi-Fi-based localization is difficult due to the limited reach of radio waves. In addition, there is the unavailability of a GNSS signal. We propose a function to link each video frame to a position based on linear interpolation using landmarks detected by the camera and image processing. Experiments for testing the accuracy of the localization in an underground sewer pipe showed that all utility holes were successfully detected as landmarks, and the maximum location estimation accuracy was less than 11.5% of the maximum interval of landmarks.

The COVID-19 pandemic and remote working did not improve WLAN security.

In this article, we present an analysis of the COVID-19 pandemic's effects on Wireless Local Area Network (WLAN) security and abundance in Southwest Finland. We hypothesised that the drastic increase in telecommuting caused by the pandemic would encourage many to update obsolete WLAN devices, improving the state of WLAN security and increasing WLAN deployment in the survey region. To test our hypotheses, data from seven WLAN surveys carried out between February 2020 and October 2021 was analysed. Surprisingly, although the results show a 50.2% increase in WLAN deployment during the second and fourth waves of the pandemic, this had no significant effect on WLAN security in the survey region. The survey data shows little change in the number of unencrypted networks and networks configured with vulnerable encryption protocols. While most of the located networks were encrypted with the secure WPA2 protocol, the number of networks configured with the newest WPA3 has not notably increased.

Testing Off-the-Shelf Optical Wireless LANs for Smart City Environments.

Optical wireless LANs (OWLs) constitute an emerging networking paradigm for indoor scenarios' fit to different smart cities' fields of applications. Commercial products employing this technology have been made available on the market in recent years. In this work, we investigate, through a set of indoor communication experiments based on commercially available products, how different environmental and usage modes affect the performance of the system, addressing the presence of multiple users, the position and mobility of the mobile devices, the handover among adjacent cells and the effect of background lighting. Our finding shows that the system is quite robust with respect to the variation of operational conditions. We show that, in most conditions, the links can reliably sustain a stable throughput, achieving at least 50% of the throughput achieved with using the maximum light intensity of the transmitting lamp, while they are affected in a very mild way by factors like position and height of the mobile device, and virtually unaffected by variations in the background light.

Optimal Access Point Power Management for Green IEEE 802.11 Networks.

In this paper, we present an approach and an algorithm aimed at minimising the energy consumption of enterprise Wireless Local Area Networks (WLANs) during periods of low user activity. We act on two network management aspects: powering off some Access Points (APs), and choosing the level of transmission power of each AP. An efficient technique to allocate the user terminals to the various APs is the key to achieving this goal. The approach has been formulated as an integer programming problem with nonlinear constraints, which comes from a general but accurate characterisation of the WLAN. This general problem formulation has two implications: the formulation is widely applicable, but the nonlinearity makes it NP-hard. To solve this problem to optimality, we devised an exact algorithm based on a customised version of Benders' decomposition method. The computational results proved the ability to obtain remarkable power savings. In addition, the good performance of our algorithm in terms of solving times paves the way for its future deployment in real WLANs.

Energy-Efficient UAVs Deployment for QoS-Guaranteed VoWiFi Service.

This paper formulates a new problem for the optimal placement of Unmanned Aerial Vehicles (UAVs) geared towards wireless coverage provision for Voice over WiFi (VoWiFi) service to a set of ground users confined in an open area. Our objective function is constrained by coverage and by VoIP speech quality and minimizes the ratio between the number of UAVs deployed and energy efficiency in UAVs, hence providing the layout that requires fewer UAVs per hour of service. Solutions provide the number and position of UAVs to be deployed, and are found using well-known heuristic search methods such as genetic algorithms (used for the initial deployment of UAVs), or particle swarm optimization (used for the periodical update of the positions). We examine two communication services: (a) one bidirectional VoWiFi channel per user; (b) single broadcast VoWiFi channel for announcements. For these services, we study the results obtained for an increasing number of users confined in a small area of 100 m2 as well as in a large area of 10,000 m2. Results show that the drone turnover rate is related to both users' sparsity and the number of users served by each UAV. For the unicast service, the ratio of UAVs per hour of service tends to increase with user sparsity and the power of radio communication represents 14-16% of the total UAV energy consumption depending on ground user density. In large areas, solutions tend to locate UAVs at higher altitudes seeking increased coverage, which increases energy consumption due to hovering. However, in the VoWiFi broadcast communication service, the traffic is scarce, and solutions are mostly constrained only by coverage. This results in fewer UAVs deployed, less total power consumption (between 20% and 75%), and less sensitivity to the number of served users.

An analytic model for Throughput Optimal Distributed Coordination Function (TO-DCF).

TO-DCF, a new backoff scheme for 802.11, has the potential to significantly increase throughput in dense wireless LANs while also opportunistically favouring nodes with heavier traffic loads and/or better channel conditions. In this paper we present an analytical model to investigate the behaviour and performance of the TO-DCF protocol with regards to operating parameters such as the number of nodes, the contention window size and the backoff countdown probabilities. We then compare numerical results from an implementation of our model with simulations. Our model shows a high level of accuracy, even when the model assumptions are relaxed, and provides guidance for network operators to correctly configure the weight functions for nodes running TO-DCF given the network's operating conditions.

Effects of Different Communication Tools on the Efficiency of Anesthesiologists in the Perioperative Setting.

OBJECTIVE: To assess if Real Time Locating Systems (RTLS) technology has an effect on the perioperative efficiency of anesthesiologists at our institution. METHODS: A retrospective chart review was performed for all outpatient and short-stay patients who received general anesthesia and monitored anesthesia care between January and June of 2016. Patients over 18 years with an ASA classification of 1, 2, and 3 were included. Time was used as a measure of efficiency between two groups of anesthesiologists.These two comparison groups were as follows: Group 1: Anesthesiologists at the academic center's main campus who do not have access to RTLSGroup 2: Anesthesiologists at Josie Robertson Ambulatory Surgical Center where RTLS is available and use of RTLS is compulsoryTwo outcome measures were collected from patient electronic records: DUR1: Duration between when patient is admitted to a presurgical bed and preoperative evaluation by the attending anesthesiologistDUR2: Duration between when patient is admitted to the operating room and initiation of induction by the attending anesthesiologist. RESULTS: Anesthesiologists who had access to RTLS technology were found to be more efficient in completing their preoperative anesthesia evaluation and initiating intraoperative induction. They took less time to complete these tasks and the difference was statistically significant to p<0.0001. CONCLUSION: Anesthesiologists at our institution, who have access to RTLS as an additional communication tool, were found to be consistently more efficient in their perioperative workflow. There are confounding factors that can account for the shorter times and more efficient perioperative workflow of anesthesiologists. With continued application and investigation over time, the utility of RTLS on workflow efficiency of healthcare providers will become more apparent.

Assistive technology using integrated flexible sensor and virtual alarm unit for blood leakage detection during dialysis therapy.

Blood leakages and blood loss are both serious complications during dialysis therapies. According to dialysis survey reports, these events are life-threatening issues for nephrology nurses, medical staff, and patients. When venous needle dislodgement occurs, it takes only <2.5 min of reaction time for blood loss in an adult patient, resulting in mortality. As an early-warning design, a wireless assistive technology using an integrated flexible sensor and virtual alarm unit was developed to detect blood leakage during dialysis therapies. The flexible sensor was designed using a screen print technique with printing electronic circuits on a plastic substrate. A self-organising algorithm was used to design a virtual alarm unit, consisting of a virtual direct current grid and a virtual alarm driver. In other words, this warning device was employed to identify the blood leakage levels via wireless fidelity wireless network in cloud computing. The feasibility was verified, and commercialisation designs can also be implemented in an embedded system.

Application Research of Using Wireless Technology to Avoid Medical Mistake / 医疗卫生装备

Objective To avoid medical mistake,improve service quality of medical care,insure the security of patients. Methods The wireless Lan was deployed in ward to implement the scheme of using wireless Lan and avoid medical mistake,and then use wireless nursing system to prove it. Results This scheme can reduce the work intensity of medical staff,decrease the probability of medical mistake,and improve the service quality of medical care. Conclusion The wireless technology can avoid medical mistake effectively.

Development Brief of Embedded Computing Technology for Mobile Wi reless Biotelemetry / 대한의료정보학회지

Embedded computing and wireless communication technology were used to develop a mobile biotelemetry system, featuring the functions of mobile measurement, wireless transmission, database archival, and internet retrieval of biomedical signals. Two PPCs (Pocket PC) with WLAN (wireless LAN) PC cards were used to simulate the communicating situation of biomedical signals between wireless sensors and a personal monitor. A PPC client program simulated the wireless sensors and a PPC server program simulated the personal medical monitor. Medical PDA was implemented by SBC (single board computer), LCD display, touch screen and Bluetooth module. Windows CE.net was ported as its operating system and the application program was developed using embedded Visual C++ 4. The measured transmission speed of ECG data was 2150 samples per second in the WLAN environment. For wireless internet connection, a Web-based server program was developed, able to display the biomedical signals of remote patients and be remotely monitored by medical doctors in a distant hospital. PDA data, which was archived at the server's database table, was transformed to an XML message and could be displayed on a Web browser as a signal graph. This system would be very useful for patients with chronic illness, especially in an emergent environment, and for containing medical cost in the aged society.

Experience and application of mobile nursing technology / 医疗卫生装备

Objective To apply modern information technology to improve the holistic nursing quality, insure the medical security and offer essential conditions for administration of medical nursing, procedure control and medical treatment navigation. Methods Special clinical mobile nursing information system was developed based on 2-dimensional bar code, special wristbands, electronic medical record, LAN technology and mobile terminal solutions. Results The system not only extremely improved the work efficiency of ward-nursing and ensured the accuracy of nursing work during special executive course, but also updated the collection of the information on time and conquered a lot of limitation of traditional hospital nursing actions. Conclusion The successful application of clinical mobile nursing system will improve the medical quality, prevent the medical negligence, enhance the nursing efficiency and management level and relieve the labor intensity. Meanwhile, being practical and convenient, this system has high value in spreading.