Search

Wireless sensor networks (WSNs) are mostly used for monitoring the environment; however, they are usually powered by non-rechargeable batteries with limited energy. Solar energy harvesting is an attractive solution to the limit by charging the sensor nodes; however, the harvested solar energy is easily affected by weather conditions. Based on the characteristics of uncertainty and intermittency of solar energy, this paper proposes a plus-profile solar energy prediction algorithm. This algorithm makes the prediction of future available solar energy by finding the data in the dataset that is most similar to the data of the day and combining it with recent weather trend. According to the predicted result, the paper further proposes an adaptive energy management scheme to suit the harvested energy. In the scheme, sensor nodes can adaptively adjust task scheduling to achieve energy neutrality. The simulation results show that compared with other algorithms, the prediction accuracy of the proposed prediction algorithm is improved by 17.7 and 22.4%, respectively, and the proposed energy management scheme reduced energy loss by 6.2 and 46.8%, respectively. [ABSTRACT FROM AUTHOR]

In the edge computing, service placement refers to the process of installing service platforms, databases, and configuration files corresponding to computing tasks on edge service nodes. In order to meet the latency requirements of new types of applications, service placement in edge computing becomes critical. The service placement strategy must be carried out in accordance with the relevant tasks within the program. However, previous research has paid little attention to related tasks within the application. If the service placement strategy does not consider task relevance, the system will frequently switch services and cause serious system overhead. In this paper, we mainly study the problem of service placement in edge computing. At the same time, we considered the issue of network access point selection during data transmission and the dependencies of task execution. We propose a Dynamic Service Placement List Scheduling (DSPLS) algorithm based on dynamic remaining task service time prediction. We conducted relevant simulation experiments, and our algorithm took the least amount of time to complete the task. [ABSTRACT FROM AUTHOR]

Mobile edge computing can meet the needs of users in real time by pushing cloud resources, such as computing, network, and storage, to the edge of a mobile network. Although mobile edge technology has brought many conveniences to mobile services, many security problems, such as mutual authentication between mobile users and servers, and the impersonation of mobile users or servers, have not been properly solved. In this paper, we propose a lightweight and secure authentication protocol to solve such security problems. We conducted a formal security analysis of our protocol using ProVerif and the Real-or-Random model to prove its correctness and security, and even if the registration center is attacked, our protocol is still secure. At the end of this paper, by comparing the communication and computing costs with other existing protocols, we prove the security and efficiency of our protocol. [ABSTRACT FROM AUTHOR]

Finding an accurate, stable and effective model to predict the rise and fall of stocks has become a task increasingly favored by scholars. This paper proposes a long short-term memory (LSTM) network based on Pearson's correlation coefficient and a Bayesian-optimized LightGBM hybrid model, named as LSTM-BO-LightGBM, to solve the problem of stock price fluctuation prediction. The multilayer bidirectional LSTM-BO-LightGBM prediction model is compared with the LSTM-BO-XGBoost hybrid model, the LSTM-LightGBM hybrid model, the LSTM-XGBoost hybrid model, the single LSTM network model and the RNN network model. The prediction result of the LSTM-BO-LightGBM model for the "ES = F" stock is an RMSE value of 596.04, MAE value of 15.24, accuracy value of 0.639 and f1_score value of 0.799, which are improved compared with the prediction results of the other five models. At the same time, when applying the model to "YM = F", "CL = F", "^TNX", "^N225", "NQ = F", "AAPL", "GC = F", "JPY = X" and "SI = F", all of the nine stocks showed good forecasting performance. The results demonstrate that the multilayer bidirectional LSTM-BO-LightGBM model proposed in this paper has better approximation ability and generalization ability in the stock fluctuation forecast than previous models and can well fit the stock fluctuation. [ABSTRACT FROM AUTHOR]

The factors affecting human comfort in office environments are complex, and numerous thermal comfort researches have been conducted by scientists. Among them, The Predicted Mean Vote (PMV) model stands among the most recognized thermal comfort models. However, there are many factors affecting comfort in office places such as illuminance, illuminance contrast, temperature, humidity, location, light color and color temperature. By analyzing the factors influencing the comfort of the office, the most important factors affecting human comfortable in the office are determined, mainly including temperature, humidity, illuminance, color temperature (THIC). By using temperature and humidity monitoring module BME280, GY30 illuminance sensor, TCS34725 full-color temperature sensor and data processing module, the data of temperature, humidity, illuminance and color temperature were collected. After collation, the comfort function of a single factor was obtained. Through a questionnaire survey, combined with analytic hierarchy process and method of two elements contrasting, the comfort model combining temperature, humidity, illumination, color temperature and other multi-factors was established. According to the characteristics of the factors, we trained the model with BP neural network algorithm. This model has a maximum recall of 95.05% and a maximum precision of 71.44%, and the average values of recall and precision after 20 times of model runs are 86.53% and 66.82%. It shows that the model can predict comfort and help control the hardware intelligently in the office. [ABSTRACT FROM AUTHOR]

The enrollment rate of freshmen has always been a headache for colleges and universities. It is also very difficult to accurately predict the number of freshmen before they register. In recent years, deep learning and machine learning technology have made a breakthrough and are widely used in data processing, edge computing, and situation awareness. So far, no researcher has used machine learning methods to forecast the enrollment of new students, because the intuitive feeling is that the registration of a freshman is very subjective, dependent on several factors. To date, the number of freshmen in universities has always been forecasted using traditional methods, that is, phone calls and fee payment status inquiries. On the basis of the historical admission enrollment data of a university, this study used a variety of machine learning methods, including decision tree, random forest, and back propagation neural network, for forecasting. Based on the results of our research, it is possible to predict whether a freshman will register in a university, which makes this work very worthy of further study. [ABSTRACT FROM AUTHOR]

In recent years, with the development of cloud computing, the Internet of Things (IoT), and other technologies, mobile intelligent transportation systems, particularly the vehicular ad hoc network (VANET), have been growing quickly. Researchers have attempted to use fog computing in VANETs in order to meet real-world requirements for their deployment. Fog computing is an extension of cloud computing, and thus, it inevitably inherits the same security challenges. Further, because VANETs are in an open network environment, they will also face several other potential security and privacy issues. In this study, to promote secure interaction in fog-based VANETs, a new authentication key exchange (AKE) scheme that uses fog nodes as relay nodes has been designed. The scheme completes mutual authentication and generates a session key for later confidential communication. The automatic verification tool ProVerif and the BAN (Burrows–Abadi–Needham) logic were used to formally verify the security of the scheme, and an informal analysis shows that it can resist multiple known attacks. The simulation and analysis results show that the proposed scheme is successful. Finally, performance evaluation shows the effectiveness of the approach. Compared with the previously proposed privacy protection authentication protocols, the results of the proposed scheme are more computationally efficient. [ABSTRACT FROM AUTHOR]