LSTM Based Neural Network Model for Anomaly Event Detection in Care-Independent Smart Homes

This study introduces a long-short-term memory(LSTM)-based neural network model developed for detecting anomaly events in care-independent smart homes,focusing on the critical application of elderly fall detection.It balances the dataset using the Synthetic Minority Over-sampling Technique(SMOTE),effectively neutralizing bias to address the challenge of unbalanced datasets prevalent in time-series classification tasks.The proposed LSTM model is trained on the enriched dataset,capturing the temporal dependencies essential for anomaly recognition.The model demonstrated a significant improvement in anomaly detection,with an accuracy of 84%.The results,detailed in the comprehensive classification and confusion matrices,showed the model’s proficiency in distinguishing between normal activities and falls.This study contributes to the advancement of smart home safety,presenting a robust framework for real-time anomaly monitoring.

An EEGA-Based Bayesian Belief Network Model for Recognition of Human Activity in Smart Home

With the emerging of sensor networks, research on sensor-based activity recognition has attracted much attention. Many existing methods cannot well deal with the cases that contain hundreds of sensors and their recognition accuracy is requisite to be further improved. A novel framework for recognizing human activities in smart home was presented. First, small, easy-to-install, and low-cost state change sensors were adopted for recording state change or use of the objects. Then the Bayesian belief network (BBN) was applied to conducting activity recognition by modeling statistical dependencies between sensor data and human activity. An edge-encode genetic algorithm (EEGA) approach was proposed to resolve the difficulties in structure learning of the BBN model under a high dimension space and large data set. Finally, some experiments were made using one publicly available dataset. The experimental results show that the EEGA algorithm is effective and efficient in learning the BBN structure and outperforms the conventional approaches. By conducting human activity recognition based on the testing samples, the BBN is effective to conduct human activity recognition and outperforms the naive Bayesian network (NBN) and multiclass naive Bayes classifier (MNBC).

Smart Home Based on Wireless Sensor-Actuator Networks

Wireless sensor-actuator networks can bring flexibility to smart home.We design and develop a smart home prototype using wireless sensor-actuator network technology to realize environmental sensing and the control of electric appliances.The basic motivation of our solution is to utilize the collaboration among a mass of low-cost sensor nodes and actuator nodes to make life convenient.To achieve it,we design a novel system architecture with assembled component modules.In particular,we address some key technical challenges:1) Field-Programmable Gate Array (FPGA) Implementation of Adaptive Differential Pulse Code Modulation (ADPCM) for audio data;2) FPGA Implementation of Lempel Ziv Storer Szymanski (LZSS) for bulk data;3) combination of complex control logic.Finally,a set of experiments are presented to evaluate the performance of our solution.

Design and Implementation of a Novel HomePlug-Based Solution for Low Cost and High Performance Smart Home Networking

As the smart home is the end-point power consumer, it is the major part to be controlled in a smart micro grid. There are so many challenges for implementing a smart home system in which the most important ones are the cost and simplicity of the implementation method. It is clear that the major share of the total cost is referred to the internal controlling system network; although there are too many methods proposed but still there is not any satisfying method at the consumers＇ point of view. In this paper, a novel solution for this demand is proposed, which not only minimizes the implementation cost, but also provides a high level of reliability and simplicity of operation; feasibility, extendibility, and flexibility are other leading properties of the design.

A Novel Probabilistic Hybrid Model to Detect Anomaly in Smart Homes

Anomaly detection in smart homes provides support to enhance the health and safety of people who live alone.Compared to the previous studies done on this topic,less attention has been given to hybrid methods.This paper presents a two-steps hybrid probabilistic anomaly detection model in the smart home.First,it employs various algorithms with different characteristics to detect anomalies from sensory data.Then,it aggregates their results using a Bayesian network.In this Bayesian network,abnormal events are detected through calculating the probability of abnormality given anomaly detection results of base methods.Experimental evaluation of a real dataset indicates the effectiveness of the proposed method by reducing false positives and increasing true positives.

Design, Implementation and Verification of Topology Network Architecture of Smart Home Tree

Smart home technology provides consumers with network connectivity,automation or enhanced services for home devices.With the Internet of Things era,a vast data flow makes business platforms have to own the same computing power to match their business services.It achieves computing power through implementing big data algorithms deployed in the cloud data center.However,because of the far long geographical distance between the client and the data center or the massive data capacity gap,potentially high latency and high packet loss will reduce the usability of smart home systems if service providers deploy all services in the cloud data center.Edge computing and fog computing can significantly improve the utilization of network resources and reconstruct the network architecture for the user’s home.This article enables a fog resource-based resource allocation management technology.It provides a method that can more reasonably allocate network resources through a virtualized middle-tier method to ensure low response time and configure Quality of Service to ensure the use of delay-sensitive critical applications to improve the reliability of smart home communication system.Besides,the proposed method has is tested and verified by adjusting the variables of the network environment.We realize the optimization of resource allocation of client network without changing the hardware of client.

The Design ＆ Implementation of Multimedia Sensor Node and the Building of Multimedia Network in Smart Home

With the requirements of multimedia service increasing in people＇ s life, sensor modules such as microphone, camera are added in the smart home＇ s sensor network, and the acquisition and processing of a large amount of information media such as audio, image and video is becoming a significant characteristics of smart home. The paper focuses on solving the following technical problems： the building of Zigbee multimedia network, the Design and selection of multimedia sensor node. These provide the basic network platform and the core technical support for the building of smart home.

A smart productivity evaluation method for shale gas wells based on 3D fractal fracture network model

The generation method of three-dimensional fractal discrete fracture network(FDFN)based on multiplicative cascade process was developed.The complex multi-scale fracture system in shale after fracturing was characterized by coupling the artificial fracture model and the natural fracture model.Based on an assisted history matching(AHM)using multiple-proxy-based Markov chain Monte Carlo algorithm(MCMC),an embedded discrete fracture modeling(EDFM)incorporated with reservoir simulator was used to predict productivity of shale gas well.When using the natural fracture generation method,the distribution of natural fracture network can be controlled by fractal parameters,and the natural fracture network generated coupling with artificial fractures can characterize the complex system of different-scale fractures in shale after fracturing.The EDFM,with fewer grids and less computation time consumption,can characterize the attributes of natural fractures and artificial fractures flexibly,and simulate the details of mass transfer between matrix cells and fractures while reducing computation significantly.The combination of AMH and EDFM can lower the uncertainty of reservoir and fracture parameters,and realize effective inversion of key reservoir and fracture parameters and the productivity forecast of shale gas wells.Application demonstrates the results from the proposed productivity prediction model integrating FDFN,EDFM and AHM have high credibility.

Zigbee-based new approach to smart home

Smart home is a promising solution to improving the quality of people＇s life. Much work has been done in the field, but most of these solutions are just based on home gateway, leaving much to be improved. One of its defects is the relatively high energy consuming and its radiation, and the other is that it is not available to the old home appliances which fail to access the internet. Full use of the low energy consuming characteristic of the Zigbee wireless sensor network, a completely new smart home solution is put forward in this paper. Without need of a home gateway and any modification for the currently used family appliances, the method uses the Zigbee coordinator as the central controller and the controllers of appliances as the end devices of Zigbee. It can realize a comfortable and smart home. Experiments show that the scheme proposed is feasible and it will be no doubt to be able to improve the quality of people＇s daily life.

TelG Mote: A Green Wireless Sensor Node Platform for Smart Home and Ambient Assisted Living

The wireless sensor network （WSN） consists of sensor nodes that interact with each other to collectively monitor environmental or physical conditions at different locations for the intended users. One of its potential deployments is in the form of smart home and ambient assisted living （SHAAL）to measure patients or elderly physiological signals, control home appliances, and monitor home. This paper focuses on the development of a wireless sensor node platform for SHAAL application over WSN which complies with the IEEE 802.15.4 standard and operates in 2.4 GHz ISM （industrial, scientific, and medical） band. The initial stage of SHAAL application development is the design of the wireless sensor node named TelG mote. The main features of TelG mote contributing to the green communications include low power consumption, wearable, flexible, user-friendly, and small sizes. It is then embedded with a self-built operating system named WiseOS to support customized operation. The node can achieve a packet reception rate （PRR） above 80% for a distance of up to 8 m. The designed TelG mote is also comparable with the existing wireless sensor nodes available in the market.

上下文感知在Smart Home系统中的应用

针对Smart Home环境的复杂性问题,提出了利用上下文技术来提高其智能化的方法。阐述了在普适环境下的上下文在智能家居环境中的重要性,介绍了上下文和上下文感知计算的定义,采用了基元组的形式定义了不同的上下文信息;提出了基于上下文感知的Smart Home系统模型,并对其功能进行了详细的描述;在Smart Home系统中,应用该模型对具体的上下文实例进行了描述和推理。

Systematic Analysis of Safety and Security Risks in Smart Homes

The revolution in Internet of Things(IoT)-based devices and applications has provided smart applications for humans.These applications range from healthcare to traffic-flow management,to communication devices,to smart security devices,and many others.In particular,government and private organizations are showing significant interest in IoT-enabled applications for smart homes.Despite the perceived benefits and interest,human safety is also a key concern.This research is aimed at systematically analyzing the available literature on smart homes and identifying areas of concern or risk with a view to supporting the design of safe and secure smart homes.For this systematic review process,relevant work in the most highly regarded journals published in the period 2016–2020(a section of 2020 is included)was analyzed.A final set of 99 relevant articles(journal articles,book sections,conference papers,and survey papers)was analyzed in this study.This analysis is focused on three research questions and relevant keywords.The systematic analysis results and key insights will help researchers and practitioners to make more informed decisions when dealing with the safety and security risks of smart homes,especially in emergency situations.

A User-Centric Approach to Activity Recognition and Guidance in Semantic Smart Home

Wireless smart home system is to facilitate people's lives and it trend to adopt a more intelligent way to provide services. It is very desirable in the recent SH market for the system to recognize users' behaviors and automatically response the corresponding activities to satisfy users' actual demands. However, activity models in the existing approaches are usually defined separately through knowledge-driven methods. These approaches cause that the activity models can't be matched with the services dynamically. To address the problem, we develop the semantic association model and a novel approach of activity recognition and guidance is presented. In our approach, the smart devices and users' requirements are described by semantic models. When the requirements are detected and understood, smart gateway can provide appropriate services, achieving activity assistance. The semantic association model allows all related elements in smart home connect with each other logically. The approach has been implemented and the results show that the success rate of the approach based on semantic association model is higher than 33% at average as compared to the approach based on predefined models. The proposed approach can effectively help people who are in trouble with learning or remembering in the common life.

A critical literature review of security and privacy in smart home healthcare schemes adopting IoT&blockchain:Problems,challenges and solutions

Protecting private data in smart homes,a popular Internet-of-Things(IoT)application,remains a significant data security and privacy challenge due to the large-scale development and distributed nature of IoT networks.Recently,smart healthcare has leveraged smart home systems,thereby compounding security concerns in terms of the confidentiality of sensitive and private data and by extension the privacy of the data owner.However,proof-of-authority(PoA)-based blockchain distributed ledger technology(DLT)has emerged as a promising solution for protecting private data from indiscriminate use and thereby preserving the privacy of individuals residing in IoT-enabled smart homes.This review elicits some concerns,issues,and problems that have hindered the adoption of blockchain and IoT(BCoT)in some domains and suggests requisite solutions using the aging-in-place scenario.Implementation issues with BCoT were examined as well as the combined challenges BCoT can pose when utilised for security gains.The study discusses recent findings,opportunities,and barriers,and provides recommendations that could facilitate the continuous growth of blockchain applications in healthcare.Lastly,the study explored the potential of using a PoA-based permission blockchain with an applicable consent-based privacy model for decision-making in the information disclosure process,including the use of publisher-subscriber contracts for fine-grained access control to ensure secure data processing and sharing,as well as ethical trust in personal information disclosure,as a solution direction.The proposed authorisation framework could guarantee data ownership,conditional access management,scalable and tamper-proof data storage,and a more resilient system against threat models such as interception and insider attacks.

Comprehensive evaluation of 5G+smart distribution network based on combined weighting method-cloud model

With the large-scale application of 5G technology in smart distribution networks,the operation effects of distribution networks are not clear.Herein,we propose a comprehensive evaluation model of a 5G+smart distribution network based on the combination weighting and cloud model of the improved Fuzzy Analytic Hierarchy-Entropy Weight Method(FAHP-EWM).First,we establish comprehensive evaluation indexes of a 5G+smart distribution network from five dimensions:reliable operation,economic operation,efficient interaction,technological intelligence,and green emission reduction.Second,by introducing the principle of variance minimization,we propose a combined weighting method based on the improved FAHP-EWM to calculate the comprehensive weight,so as to reduce the defects of subjective arbitrariness and promote objectivity.Finally,a comprehensive evaluation model of 5G+smart distribution network based on cloud model is proposed by considering the uncertainty of distribution network node information and equipment status information.The example analysis indicates that the overall operation of the 5G+smart distribution network project is decent,and the weight value calculated by the combined weighting method is more reasonable and accurate than that calculated by the single weighting method,which verifies the effectiveness and rationality of the proposed evaluation method.Moreover,the proposed evaluation method has a certain guiding role for the large-scale application of 5G communication technology in smart distribution networks.

Risk Identification based on Hidden Semi-Markov Model in Smart Distribution Network

The smart distribution system is the critical part of the smart grid, which also plays an important role in the safe and reliable operation of the power grid. The self-healing function of smart distribution network will effectively improve the security, reliability and efficiency, reduce the system losses, and promote the development of sustainable energy of the power grid. The risk identification process is the most fundamental and crucial part of risk analysis in the smart distribution network. The risk control strategies will carry out on fully recognizing and understanding of the risk events and the causes. On condition that the risk incidents and their reason are identified, the corresponding qualitative / quantitative risk assessment will be performed based on the influences and ultimately to develop effective control measures. This paper presents the concept and methodology on the risk identification by means of Hidden Semi-Markov Model (HSMM) based on the research of the relationship between the operating characteristics/indexes and the risk state, which provides the theoretical and practical support for the risk assessment and risk control technology.

Anomalous Power-Usage Behavior Detection from Smart Home Wireless Communications

With the rapid development of Internet of things(IoT)technologies,smart home systems are getting more and more popular in our daily life.Besides provid-ing convenient functionality and tangible benefits,smart home systems expose users to security risks.In this paper,we proposed SHGuard,an anomaly detection approach based on power usage data exposed from wireless commu-nications in the smart home system.SHGuard monitors and collects the electricity-usage data sent from the smart sockets.Based on the collected data,we developed a method to identify/infer the type of device and formally defined the user behavior pattern according to the device event features,e.g.,frequent sequence pattern set,the support degree,the sequence length and the occurrence time of the power changing event.SHGuard extracts and builds the normal behavior pattern during the initialization stage.It continuously infers the smart devices’states by monitoring the electricity usage data and updates the user behavior patterns.Any abnormal behaviors will be detected once the current user behavior pattern deviates from the original pattern.We prototyped our method and evaluated SHGuard using UCI dataset.The experiment results illustrated the efficiency of SHGuard.

Applications of smart proxies for subsurface modeling

Using artificial intelligence(AI) and machine learning(ML) techniques, we developed and validated the smart proxy models for history matching of reservoir simulation, sensitivity analysis, and uncertainty assessment by artificial neural network(ANN). The smart proxy models were applied on two cases, the first case study investigated the application of a proxy model for calibrating a reservoir simulation model based on historical data and predicting well production while the second case study investigated the application of an ANN-based proxy model for fast-track modeling of CO2 enhanced oil recovery, aiming at the prediction of the reservoir pressure and phase saturation distribution at injection stage and post-injection stage. The prediction effects for both cases are promising. While a single run of basic numerical simulation model takes hours to days, the smart proxy model runs in a matter of seconds, saving 98.9% of calculating time. The results of these case studies demonstrate the advantage of the proposed workflow for addressing the high run-time, computational time and computational cost of numerical simulation models. In addition, these proxy models predict the outputs of reservoir simulation models with high accuracy.

Research on Cyber-Physical Modeling for Smart Distribution Grid

Smart distribution network will achieve the optimal operation of the distribution network, provide high-quality and reliable power, guarantee the development of modern social economy. The deep integration of cyber system and power physical system is the key to smart distribution network. The emergence of cyber-physical system (CPS) provides a new way to solve this problem, the cyber-physical model for smart distribution grid becomes an urgent problem to be solved. In this paper, the content and method of cyber-physical model for smart distribution grid are analyzed by combining with the coupling of information flow and power flow of smart distribution network from the perspective of cyber-physical model. At last, taking 110 kV typical substation as an example, the coupling mechanism and function of power flow and information flow is studied.

Vulnerability Detection of Ethereum Smart Contract Based on SolBERT-BiGRU-Attention Hybrid Neural Model

In recent years,with the great success of pre-trained language models,the pre-trained BERT model has been gradually applied to the field of source code understanding.However,the time cost of training a language model from zero is very high,and how to transfer the pre-trained language model to the field of smart contract vulnerability detection is a hot research direction at present.In this paper,we propose a hybrid model to detect common vulnerabilities in smart contracts based on a lightweight pre-trained languagemodel BERT and connected to a bidirectional gate recurrent unitmodel.The downstream neural network adopts the bidirectional gate recurrent unit neural network model with a hierarchical attention mechanism to mine more semantic features contained in the source code of smart contracts by using their characteristics.Our experiments show that our proposed hybrid neural network model SolBERT-BiGRU-Attention is fitted by a large number of data samples with smart contract vulnerabilities,and it is found that compared with the existing methods,the accuracy of our model can reach 93.85%,and the Micro-F1 Score is 94.02%.