Due to the Internet of Things popularity, many agricultural data are collected by sensors automatically. The abundance of agricultural data makes precise prediction of rice yield possible. Because the climate factors have an essential effect on the rice yield, we considered the climate factors in the prediction model. Accordingly, this paper proposes a machine learning model for rice yield prediction in Taiwan, including the genetic algorithm and support vector regression model. The dataset of this study includes the meteorological data from the Central Weather Bureau and rice yield of Taiwan from 2003 to 2019. The experimental results show the performance of the proposed model is nearly 30% better than MARS, RF, ANN, and SVR models. The most important climate factors affecting the rice yield are the total sunshine hours, the number of rainfall days, and the temperature.The proposed model also offers three advantages: (a) the proposed model can be used in different geographical regions with high prediction accuracies; (b) the proposed model has a high explanatory ability because it could select the important climate factors which affect rice yield; (c) the proposed model is more suitable for predicting rice yield because it provides higher reliability and stability for predicting. The proposed model can assist the government in making sustainable agricultural policies.

We construct a deep neural network model named ECGResNet. This model can diagnosis diseases based on 12-lead ECG data of eight common cardiovascular diseases with a high accuracy. We chose the 16 Blocks of ResNet50 as the main body of the model and added the Squeeze-and-Excitation module to learn the data information between channels adaptively. We modified the first convolutional layer of ResNet50 which has a convolutional kernel of 7 to a superposition of convolutional kernels of 8 and 16 as our feature extraction method. This way allows the model to focus on the overall trend of the ECG signal while also noticing subtle changes. The model further improves the accuracy of cardiovascular and cerebrovascular disease classification by using a fully connected layer that integrates factors such as gender and age. The ECGResNet model adds Dropout layers to both the residual block and SE module of ResNet50, further avoiding the phenomenon of model overfitting. The model was eventually trained using a five-fold cross-validation and Flooding training method, with an accuracy of 95% on the test set and an F1-score of 0.841.We design a new deep neural network, innovate a multi-scale feature extraction method, and apply the SE module to extract features of ECG data.

Diversified SaaS applications allow users more choices to use, according to their own preferences. However, the diversification of SaaS applications also makes it impossible for users to choose the best one. Furthermore, users can't take advantage of the functionality between SaaS applications. In this paper, we propose a platform that provides an SaaS mashup service, by extracting interoperable service functions from SaaS-based applications that independent vendors deploy and supporting a customized service recommendation function through log data binding in the cloud environment. The proposed SaaS mashup service platform consists of a SaaS aggregation framework and a log data binding framework. Each framework was concreted by using Apache Kafka and rule matrix-based recommendation techniques. We present the theoretical basis of implementing the high-performance message-processing function using Kafka. The SaaS mashup service platform, which provides a new type of mashup service by linking SaaS functions based on the above technology described, allows users to combine the required service functions freely and access the results of a rich service-utilization experience, using the SaaS mashup function. The platform developed through SaaS mashup service technology research will enable various flexible SaaS services, expected to contribute to the development of the smart-contents industry and the open market.

Recently, the importance and necessity of artificial intelligence (AI), especially machine learning, has been emphasized. In fact, studies are actively underway to solve complex and challenging problems through the use of AI systems, such as intelligent CCTVs, intelligent AI security systems, and AI surgical robots. Information security that involves analysis and response to security vulnerabilities of software is no exception to this and is recognized as one of the fields wherein significant results are expected when AI is applied. This is because the frequency of malware incidents is gradually increasing, and the available security technologies are limited with regard to the use of software security experts or source code analysis tools. We conducted a study on MalDC, a technique that converts malware into images using machine learning, MalDC showed good performance and was able to analyze and classify different types of malware. MalDC applies a preprocessing step to minimize the noise generated in the image conversion process and employs an image augmentation technique to reinforce the insufficient dataset, thus improving the accuracy of the malware classification. To verify the feasibility of our method, we tested the malware classification technique used by MalDC on a dataset provided by Microsoft and malware data collected by the Korea Internet & Security Agency (KISA). Consequently, an accuracy of 97% was achieved.

The number of interconnected real-world devices such as sensors, actuators, and physical devices has increased with the advancement of technology. Due to this advancement, users face difficulties searching for the location of these devices, and the central issue is the findability of Things. In the WoT environment, keyword-based and geospatial searching approaches are used to locate these devices anywhere and on the web interface. A few static methods of indexing and ranking are discussed in the literature, but they are not suitable for finding devices dynamically. The authors have proposed a mechanism for dynamic and efficient searching of the devices in this paper. Indexing and ranking approaches can improve dynamic searching in different ways. The present paper has focused on indexing for improving dynamic searching and has indexed the Things Description in Solr. This paper presents the Things Description according to the model of W3C JSON-LD along with the open-access APIs. Search efficiency can be analyzed with query response timings, and the accuracy of response timings is critical for search results. Therefore, in this paper, the authors have evaluated their approach by analyzing the search query response timings and the accuracy of their search results. This study utilized different indexing approaches such as key-words-based, spatial, and hybrid. Results indicate that response time and accuracy are better with the hybrid approach than with keyword-based and spatial indexing approaches.

This article shows a set of physical information fusion IoT systems that we designed for smart buildings. Its essence is a computer system that combines physical quantities in buildings with quantitative analysis and control. In the part of the Internet of Things, its mechanism is controlled by a monitoring system based on sensor networks and computer-based algorithms. Based on the design idea of the agent, we have realized human-machine interaction (HMI) and machine-machine interaction (MMI). Among them, HMI is realized through human-machine interaction, while MMI is realized through embedded computing, sensors, controllers, and execution. Device and wireless communication network. This article mainly focuses on the function of wireless sensor networks and MMI in environmental monitoring. This function plays a fundamental role in building security, environmental control, HVAC, and other smart building control systems. The article not only discusses various network applications and their implementation based on agent design but also demonstrates our collaborative information fusion strategy. This strategy can provide a stable incentive method for the system through collaborative information fusion when the sensor system is unstable in the physical measurements, thereby preventing system jitter and unstable response caused by uncertain disturbances and environmental factors. This article also gives the results of the system test. The results show that through the CPS interaction of HMI and MMI, the intelligent building IoT system can achieve comprehensive monitoring, thereby providing support and expansion for advanced automation management.

Latest technological innovation in the development of compact lower power radios has led to the explosion of Internet of Things. With Wi-Fi, Zigbee and other physical layer protocols offering short coverage area there was a need for a RF protocol that had a larger coverage area with low power consumption. LoRa offers Long Range with lower power consumption. LoRa offers point to point and point to multipoint connections. with Single hop communication in place the need for routing protocols are eliminated. LoRa Wide Area Network stack can accommodate thousands of nodes under a single LoRa gateway with a single hop communication between the end nodes and LoRaWAN gateway. This paper takes an experimental approach to analyze the basic physical layer parameters of LoRa and the practical coverage offered by a LoRaWAN under highly dense urban conditions with variable topography. The insights gained from the practical deployment of the LoRaWAN network, and the subsequent performance analysis is used to design a novel public utility monitoring platform. The second half of the papers is designing a robust platform to integrate both existing wired sensor water meters, current and future generation wireless water meters. The Common Automated Metering Platform is designed to integrate both wired sensors and wireless (LoRaWAN and Wi-Fi) supported water meters. This integrated platform reduces the number of nodes under each LoRaWAN gateway and thus improves the scalability of the network. This architecture is currently designed to accommodate one utility application but can be modified to integrate multi-utility applications.

Context: Testing is one of the techniques that can assure the quality of software including the domain of Software Product Line (SPL). Various techniques have been deliberated to enhance the quality of SPL including Model-based Testing (MBT). Objective: The objective of this study is to analyze and classify trends of MBT in SPL covering the solutions, issues and evaluation aspects by using taxonomy form. Method: A Systematic Literature Review (SLR) was conducted involving 63 primary studies from different sources. The selected studies were categorized based on their common characteristics. Results: Several findings can guide future research on MBT for SPL. The important finding is that the multiple measurements are still open to improving current metrics to evaluate test cases in MBT for SPL. The multiple types of measurement required a trade-off between maximization and minimization results to ensure the testing method which could satisfy multiple test criteria for example cost and effectiveness at the same time.

According to a survey published in an authoritative journal in January 2020, the globalincidence rate of mental illness is 8.3% for men and 10.6% for women, which indicates thatmental illness has become a globally recognized obstacle. Therefore, specific psychotherapy including mental illness will become an important research topic. It is very effective forpatients with special mental diseases, such as mental illness, to reduce their mental reaction byexposure therapy; the system uses the virtual reality system of medical images processed by learningalgorithm to reproduce the effect of virtual reality exposure method of the high scene of transparent ladder. Compared with the old invasive exposure scene, the results show that theimprovement of both conditions has obvious effect, and the effect of human treatment underthe two conditions is not good. There are obvious differences, which show that virtual reality model will gradually replace the on-the-spot feeling. Finally, with more and more researchers have put forward a variety of other virtual reality image processing models, the research of image processing has gradually become more and more interested.

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

At EUROCRYPT 2019, a new block cipher algorithm called BISON was proposed by Canteaut et al. which uses a novel structure named as Whitened Swap-Or-Not (WSN). Unlike the traditional wide trail strategy, the differential and linear properties of this algorithm can be easily determined. However, the encryption speed of the BISON algorithm is quite low due to a large number of iterative rounds needed to ensure certain security margins. Commonly, denoting by n is the data block length, this design requires 3n encryption rounds. Moreover, the block size n of BISON is always odd, which is not convenient for operations performed on a byte level. In order to overcome these issues, we propose a new block cipher, named DBISON, which more efficiently employs the ideas of double layers typical to the BISON-like construction. More precisely, DBISON divides the input into two parts of size n/2 bits and performs the round computations in parallel, which leads to an increased encryption speed. In particular, the data block length n of DBISON can be even, which gives certain additional implementation benefits over BISON. Furthermore, the resistance of DBISON against differential and linear attacks is also investigated. It is shown the maximal differential probability (MDP) is 1/2^n-1 for n encryption rounds and that the maximal linear probability (MLP) is strictly less than 1/2^n-1 when (n/2+3) iterative encryption rounds are used. These estimates are very close to the ideal values when n is close to 256.

Due to the increasing need for data sharing in the age of big data, how to achieve data access control and implement user permission revocation in the blockchain environment becomes an urgent problem. To solve the above problems, we propose a novel blockchain-based data sharing scheme (BDSS) with fine-grained access control and permission revocation in this paper, which regards the medical environment as the application scenario. In this scheme, we separate the public part and private part of the electronic medical record (EMR). Then, we use symmetric searchable encryption (SSE) technology to encrypt these two parts separately, and use attribute-based encryption (ABE) technology to encrypt symmetric keys which used in SSE technology separately. This guarantees better fine-grained access control and makes patients to share data at ease. In addition, we design a mechanism for EMR permission grant and revocation so that hospital can verify attribute set to determine whether to grant and revoke access permission through blockchain, so it is no longer necessary for ciphertext re-encryption and key update. Finally, security analysis, security proof and performance evaluation demonstrate that the proposed scheme is safe and effective in practical applications.

The fear that location privacy may be compromised greatly hinders the development of location-based service. Accordingly, some schemes based on the distributed architecture in peer-to-peer network for location privacy protection are proposed. Most of them assume that mobile terminals are mutually trusted, but this does not conform to realistic scenes, and they cannot make requirements for the level of location privacy protection. Therefore, this paper proposes a scheme for location attribute-based security authentication and private sharing data group, so that they trust each other in peer-to-peer network and the trusted but curious mobile terminal cannot access the initiator's query request. A new identifier is designed to allow mobile terminals to customize the protection strength. In addition, the caching mechanism is introduced considering the cache capacity, and a cache replacement policy based on deep reinforcement learning is proposed to reduce communications with location-based service server for achieving location privacy protection. Experiments show the effectiveness and efficiency of the proposed scheme.

Face manipulation tools represented by Deepfake have threatened the security of people's biological identity information. Particularly, manipulation tools with deep learning technology have brought great challenges to Deepfake detection. There are many solutions for Deepfake detection based on traditional machine learning and advanced deep learning. However, those solutions of detectors almost have problems of poor performance when evaluated on different quality datasets. In this paper, for the sake of making high-quality Deepfake datasets, we provide a preprocessing method based on the image pixel matrix feature to eliminate similar images and the residual channel attention network (RCAN) to resize the scale of images. Significantly, we also describe a Deepfake detector named Cascaded-Hop which is based on the PixelHop++ system and the successive subspace learning (SSL) model. By feeding the preprocessed datasets, Cascaded-Hop achieves a good classification result on different manipulation types and multiple quality datasets. According to the experiment on FaceForensics++ and Celeb-DF, the AUC (area under curve) results of our proposed methods are comparable to the state-of-the-art models.

With the development of multiuser online meetings, more group-oriented technologies and applications for instance collaborative work are becoming increasingly important. Authenticated Group Key Agreement (AGKA) schemes provide a shared group key for users with after their identities are confirmed to guarantee the confidentiality and integrity of group communications. On the basis of the Public Key Cryptography (PKC) system used, AGKA can be classified as Public Key Infrastructure-based, Identity-based, and Certificateless. Because the latter type can solve the certificate management overhead and the key escrow problems of the first two types, Certificateless-AGKA (CL-AGKA) protocols have become a popular area of research. However, most CL-AGKA protocols are vulnerable to Public Key Replacement Attacks (PKRA) due to the lack of public key authentication. In the present work, we present a CL-AGKA scheme that can resist PKRA in order to solve impersonation attacks caused by those attacks. Beyond security, improving scheme efficiency is another direction for AGKA research. To reduce the communication and computation cost, we present a scheme with only one round of information interaction and construct a CL-AGKA scheme replacing the bilinear pairing with elliptic curve cryptography. Therefore, our scheme has good applicability to communication environments with limited bandwidth and computing capabilities.

In the development of logistics system, the breakthrough of important technologies such as technology platform for logistics information management and control is the key content of the study. Based on Javascript and JQuery, the logistics system realizes real-time monitoring, collection of historical status data, statistical analysis and display, intelligent recommendation and other functions. In order to strengthen the cooperation of warehouse storage, enhance the utilization rate of resources, and achieve the purpose of real-time and visual supervision of transportation equipment and cargo tracking, this paper studies the VNF dynamic deployment and SFC routing problem in the network load change scenario based on the logistics system. The BIP model is used to model the VNF dynamic deployment and routing problem. The optimization objective is to minimize the total cost overhead generated by each SFCR. Furthermore, the application of the SFC mapping algorithm in the routing topology solving problem is proposed. Based on the concept of relative cost and the idea of topology transformation, the SFC-map algorithm can efficiently complete the dynamic deployment of VNF and the routing calculation of SFC by using multi-layer graph. In the simulation platform based on the logistics system, the proposed algorithm is compared with VNF-DRA algorithm and Provision Traffic algorithm in the network receiving rate, throughput, path end-to-end delay, deployment number, running time and utilization rate. According to the test results, it is verified that the test results of the optimization algorithm in this paper are obviously improved compared with the comparison method, and it has higher practical application and promotion value.

The reliability and performance of WiFi need optimization because of the rising number of WiFi users day by day. A highlighted point is saving power while transmitting and receiving packets using WiFi devices. Wake-on-Wlan (WoW) is also implemented to improve energy consumption, but it also needs betterment. This paper will introduce universal ideas to transmit and receive packets using low-power technology like Bluetooth or BLE (Bluetooth low energy). While looking for power-saving ways in this research, WiFi connection and maintenance also take care using lesser power-consuming technology. Identifying different use-cases where low power technology can help save energy and maintain 802.11 connection is part of the research. In addition, the proposed method discuss energy saving with unicast and broadcast/multicast data. Calculation of power-saving and comparison with standalone WiFi usage clearly shows the effectiveness of the proposed method.

The development of wireless communication technology has led to the underutilization of radio spectra. To address this limitation, an intelligent cognitive radio network was developed. Specific emitter identification (SEI) is a key technology in this network. However, in realistic non-cooperative scenarios, the system may detect signal classes beyond those in the training database, and only a few labeled signal samples are available for network training, both of which deteriorate identification performance. To overcome these challenges, a meta-learning-based open-set identification system is proposed for SEI. First, the received signals were pre-processed using bi-spectral analysis and a Radon transform to obtain signal representation vectors, which were then fed into an open-set SEI network. This network consisted of a deep feature extractor and an intrinsic feature memorizer that can detect signals of unknown classes and classify signals of different known classes. The training loss functions and the procedures of the open-set SEI network were then designed for parameter optimization. Considering the few-shot problems of open-set SEI, meta-training loss functions and meta-training procedures that require only a few labeled signal samples were further developed for open-set SEI network training. The experimental results demonstrate that this approach outperforms other state-of-the-art SEI methods in open-set scenarios. In addition, excellent open-set SEI performance was achieved using at least 50 training signal samples, and effective operation in low signal-to-noise ratio (SNR) environments was demonstrated.