The MobileNetV3 is specially designed for mobile devices with limited memory and computing power. To reduce the network parameters and improve the network inference speed, a new lightweight network is proposed based on MobileNetV3. Firstly, to reduce the computation of residual blocks, a partial residual structure is designed by dividing the input feature maps into two parts. The designed partial residual structure is used to replace the residual block in MobileNetV3. Secondly, a dual-path feature extraction structure is designed to further reduce the computation of MobileNetV3. Different convolution kernel sizes are used in the two paths to extract feature maps with different sizes. Besides, a transition layer is also designed for fusing features to reduce the influence of the new structure on accuracy. The CIFAR-100 dataset and Image Net dataset are used to test the performance of the proposed partial residual structure. The ResNet based on the proposed partial residual structure has smaller parameters and FLOPs than the original ResNet. The performance of improved MobileNetV3 is tested on CIFAR-10, CIFAR-100 and ImageNet image classification task dataset. Comparing MobileNetV3, GhostNet and MobileNetV2, the improved MobileNetV3 has smaller parameters and FLOPs. Besides, the improved MobileNetV3 is also tested on CPU and Raspberry Pi. It is faster than other networks

Accurate liver segment segmentation based on radiological images is indispensable for the preoperative analysis of liver tumor resection surgery. However, most of the existing segmentation methods are not feasible to be used directly for this task due to the challenge of exact edge prediction with some tiny and slender vessels as its clinical segmentation criterion. To address this problem, we propose a novel deep learning based segmentation model, called Boundary-Aware Dual Attention Liver Segment Segmentation Model (BADA). This model can improve the segmentation accuracy of liver segments with enhancing the edges including the vessels serving as segment boundaries. In our model, the dual gated attention is proposed, which composes of a spatial attention module and a semantic attention module. The spatial attention module enhances the weights of key edge regions by concerning about the salient intensity changes, while the semantic attention amplifies the contribution of filters that can extract more discriminative feature information by weighting the significant convolution channels. Simultaneously, we build a dataset of liver segments including 59 clinic cases with dynamically contrast enhanced MRI(Magnetic Resonance Imaging) of portal vein stage, which annotated by several professional radiologists. Comparing with several state-of-the-art methods and baseline segmentation methods, we achieve the best results on this clinic liver segment segmentation dataset, where Mean Dice, Mean Sensitivity and Mean Positive Predicted Value reach 89.01%, 87.71% and 90.67%, respectively.

Web services instances can be classified into two categories, namely trusted and untrusted from users. A web service with high throughput (TP) and low response time (RT) instance values is a trusted web service. Web services are not trustworthy due to the mismatch in the guaranteed instance values and the actual values achieved by users. To perform web services selection from users' attained TP and RT values, we need to verify the correct prediction of trusted and untrusted instances from invoked web services. This accurate prediction of web services instances is used to perform the selection of web services. We propose to construct fuzzy rules to label web services instances correctly. This paper presents web services selection using a well-known machine learning algorithm, namely REPTree, for the correct prediction of trusted and untrusted instances. Performance comparison of REPTree with five machine learning models is conducted on web services datasets. We have performed experiments on web services datasets using a ten k-fold cross-validation method. To evaluate the performance of the REPTree classifier, we used accuracy metrics (Sensitivity and Specificity). Experimental results showed that web service (WS1) gained top selection score with the (47.0588%) trusted instances, and web service (WS2) was selected the least with (25.00%) trusted instances. Evaluation results of the proposed web services selection approach were found as (asymptotic sig. = 0.019), demonstrating the relationship between final selection and recommended trust score of web services.

The U-Net architecture-based segmentation models attained remarkable performance in numerous medical image segmentation missions like skin lesion segmentation. Nevertheless, the resolution gradually decreases and the loss of spatial information increases with deeper network. The fusion of adjacent layers is not enough to make up for the lost spatial information, thus resulting in errors of segmentation boundary so as to decline the accuracy of segmentation. To tackle the issue, we propose a new deep learning-based segmentation model. In the decoding stage, the feature channels of each decoding unit are concatenated with all the feature channels of the upper coding unit. Which is done in order to ensure the segmentation effect by integrating spatial and semantic information, and promotes the robustness and generalization of our model by combining the atrous spatial pyramid pooling (ASPP) module and channel attention module (CAM). Extensive experiments on ISIC2016 and ISIC2017 common datasets proved that our model implements well and outperforms compared segmentation models for skin lesion segmentation.

Nowadays, artificial intelligence promotes the rapid development of skin cancer detection technology, and the federated skin cancer detection model (FSDM) and dual generative adversarial network model (DGANM) solves the fragmentation and privacy of data to a certain extent. To overcome the problem that the many-objective evolutionary algorithm (MaOEA) cannot guarantee the convergence and diversity of the population when solving the above models, a many-objective evolutionary algorithm based on integrated strategy (MaOEA-IS) is proposed. First, the idea of federated learning is introduced into population mutation, the new parents are generated through sub-populations employs different mating selection operators. Then, the distance between each solution to the ideal point (SID) and the Achievement Scalarizing Function (ASF) value of each solution are considered comprehensively for environment selection, meanwhile, the elimination mechanism is used to carry out the select offspring operation. Eventually, the FSDM and DGANM are solved through MaOEA-IS. The experimental results show that the MaOEA-IS has better convergence and diversity, and it has superior performance in solving the FSDM and DGANM. The proposed MaOEA-IS provides more reasonable solutions scheme for many scholars of skin cancer detection and promotes the progress of intelligent medicine.

Smart power grid is a user friendly system that transforms the traditional electric grid to the one that operates in a co-operative and reliable manner. Demand Response (DR) is one of the important components of the smart grid. The DR programs enable the end user participation by which they can communicate with the electricity service provider and shape their daily energy consumption patterns and reduce their consumption costs. The increasing demands of electricity owing to growing population stresses the need for optimal usage of electricity and also to look out alternative and cheap renewable sources of electricity. The solar and wind energy are the promising sources of alternative energy at present because of renewable nature and low cost implementation. The proposed work models a smart home with renewable energy units. The random nature of the renewable sources like wind and solar energy brings an uncertainty to the model developed. A stochastic dual descent optimization method is used to bring optimality to the developed model. The proposed work is validated using the simulation results. From the results it is concluded that proposed work brings a balanced usage of the grid power and the renewable energy units. The work also optimizes the daily consumption pattern thereby reducing the consumption cost for the end users of electricity.

Automated medical claims processing and billing is a popular application domain of information technology. Managing medical related data is a tedious job for healthcare professionals, which distracts them from their main job of healthcare. The technology used in data management has a sound impact on the quality of healthcare data. Most of Information Technology (IT) organizations use conventional software development technology for the implementation of healthcare systems. The objective of this experimental study is to devise a mechanism for use of rule-based expert systems in medical related edits and compare it with the conventional software development technology. A sample of 100 medical edits is selected as a dataset to be tested for implementation using both technologies. Besides empirical analysis, paired t-test is also used to validate the statistical significance of the difference between the two techniques. The conventional software development technology took 254.5 working hours, while rule-based technology took 81 hours to process these edits. Rule-based technology outperformed the conventional systems by increasing the confidence value to 95% and reliability measure to 0.462 (which is < 0.5) which is three times more efficient than conventional software development technology.

Rice is a fundamental staple food commodity all around the world. Globally, it is grown over 167 million hectares and occupies almost 1/5^th of total cultivated land under cereals. With a total production of 782 million metric tons in 2018. In Pakistan, it is the 2^nd largest crop being produced and 3^rd largest food commodity after sugarcane and rice. The stem borers a type of pest in rice and other crops, Scirpophaga incertulas or the yellow stem borer is very serious pest and a major cause of yield loss, more than 90% damage is recorded in Pakistan on rice crop. Yellow stem borer population of rice could be stimulated with various environmental factors which includes relative humidity, light, and environmental temperature. Focus of this study is to find the environmental factors changes i.e., temperature, relative humidity and rainfall that can lead to cause outbreaks of yellow stem borers. this study helps to find out the hot spots of insect pest in rice field with a control of farmer's palm. Proposed system uses temperature, relative humidity, and rain sensor along with artificial neural network to predict yellow stem borer attack and generate warning to take necessary precautions. result shows 85.6% accuracy and accuracy gradually increased after repeating several training rounds. This system can be good IoT based solution for pest attack prediction which is cost effective and accurate.

In this study, the authors intend to analyze factors contributing to research performance using Backpropagation Neural Network and Support Vector Machine. The analyzing factors contributing to lecturer research performance start from defining the features. The next stage is to collect datasets based on defining features. Then transform the raw dataset into data ready to be processed. After the data is transformed, the next stage is the selection of features. Before the selection of features, the target feature is determined, namely research performance. The selection of features consists of Chi-Square selection (U), and Pearson correlation coefficient (CM). The selection of features produces eight factors contributing to lecturer research performance are Scientific Papers (U: 154.38, CM: 0.79), Number of Citation (U: 95.86, CM: 0.70), Conference (U: 68.67, CM: 0.57), Grade (U: 10.13, CM: 0.29), Grant (U: 35.40, CM: 0.36), IPR (U: 19.81, CM: 0.27), Qualification (U: 2.57, CM: 0.26), and Grant Awardee (U: 2.66, CM: 0.26). To analyze the factors, two data mining classifiers were involved, Backpropagation Neural Networks (BPNN) and Support Vector Machine (SVM). Evaluation of the data mining classifier with an accuracy score for BPNN of 95 percent, and SVM of 92 percent. The essence of this analysis is not to find the highest accuracy score, but rather whether the factors can pass the test phase with the expected results. The findings of this study reveal the factors that have a significant impact on research performance and vice versa.

Recent studies have focused on self-management of hypertension using smart devices (cellular phones, tablets, watches). It has proven to be an effective tool for early detection and control of high Blood Pressure (BP) without affecting patients' daily routines. This systematic review surveys the existing self-monitoring systems, evaluate their effectiveness and compares the different approaches. We investigated the current systems in terms of various attributes, including methods used, sample size, type of investigation, inputs/ outputs, rate of success in controlling BP, group of users with higher response rate and beneficiaries, acceptability, and adherence to the system. We identified some limitations, shortcomings, and gaps in the research conducted recently studying the impact of mobile technology on managing hypertension. These shortcomings can generate future research opportunities and enable it to become more realistic and adaptive. We recommended including more observable factors and human behaviors that affect BP. Furthermore, we suggested that vital monitoring/logging and medication tuning are insufficient to improve hypertension control. There is also a need to observe and alter patient behavior and lifestyles.

As a promising technique to support tremendous numbers of Internet of Things devices and a variety of applications efficiently, mobile edge computing (MEC) has attracted extensive studies recently. In this paper, we consider a MEC-assisted peer-to-peer (P2P) mobile communication system where MEC servers are deployed at access points to accelerate the communication process between mobile terminals. To capture the tradeoff between the time delay and the energy consumption of the system, a cost function is introduced to facilitate the optimization of the computation and communication resources. The formulated optimization problem is non-convex and is tackled by an iterative block coordinate descent algorithm that decouples the original optimization problem into two subproblems and alternately optimizes the computation and communication resources. Moreover, the MEC-assisted P2P communication system is compared with the conventional P2P communication system, then a condition is provided in closed-form expression when the MEC-assisted P2P communication system performs better. Simulation results show that the advantage of this system is enhanced when the computing capability of the receiver increases whereas it is reduced when the computing capability of the transmitter increases. In addition, the performance of this system is significantly improved when the signal-to-noise ratio of hop-1 exceeds that of hop-2.

In image segmentation, for the condition that objects (targets) and background in an image are intertwined or their common boundaries are vague as well as their textures are similar, and the targets in images are greatly variable, the deep learning might be difficult to use. Hence, a new method based on graph theory and guided feathering is proposed. First, it uses a guided feathering algorithm to initially separate the objects from background roughly, then, the image is separated into two different images: foreground image and background image, subsequently, the two images are segmented accurately by using the improved graph-based algorithm respectively, and finally, the two segmented images are merged together as the final segmentation result. For the graph-based new algorithm, it is improved based on MST in three main aspects: (1) the differences between the functions of intra-regional and inter-regional; (2) the function of edge weight; and (3) re-merge mechanism after segmentation in graph mapping. Compared to the traditional algorithms such as region merging, ordinary MST and thresholding, the studied algorithm has the better segmentation accuracy and effect, therefore it has the significant superiority.

With the improvement of people's living standards and the development of tourism, tourists have greater freedom in choosing destinations. Therefore, as an indicator of satisfaction with scenic spots, tourist comments are becoming increasingly prominent. This paper aims to compare and analyze the landscape image of the Five Great Mountains in China and provide specific strategies for its development. The online reviews of tourists on the Online Travel Agency (OTA) website about the Five Great Mountains from 2015 to 2018 are collected as research samples. The text analysis method and R language are used to analyze the content of the tourist reviews, while the high-frequency words in the word cloud are used for visual display. In addition, the entropy weight method is used to determine the index weight and tourist satisfaction is evaluated to understand the weaknesses of those scenic spots. The results of the study show that firstly, the tourist satisfaction with the Five Great Mountains is basically consistent with its popularity. Secondly, through weight analysis, tourists pay special attention to the landscape features and environmental health of the scenic area, so that relevant departments should focus on building the landscape characteristics and improving the environmental health of the scenic area. At the same time, the accommodation and service management of the scenic spot cannot be ignored. Finally, according to the analysis results, suggestions are made on how to improve the tourist satisfaction with the Five Great Mountains.

In response to problems such as insufficient extraction information, low detection accuracy, and frequent misdetection in the field of Thangka image defects, this paper proposes a YOLOv5 prediction algorithm fused with the attention mechanism. Firstly, the Backbone network is used for feature extraction, and the attention mechanism is fused to represent different features, so that the network can fully extract the texture and semantic features of the defect area. The extracted features are then weighted and fused, so as to reduce the loss of information. Next, the weighted fused features are transferred to the Neck network, the semantic features and texture features of different layers are fused by FPN, and the defect target is located more accurately by PAN. In the detection network, the CIOU loss function is used to replace the GIOU loss function to locate the image defect area quickly and accurately, generate the bounding box, and predict the defect category. The results show that compared with the original network, YOLOv5-SE and YOLOv5-CBAM achieve an improvement of 8.95% and 12.87% in detection accuracy respectively. The improved networks can identify the location and category of defects more accurately, and greatly improve the accuracy of defect detection of Thangka images.

Public key encryption with keyword search (PEKS) allows a user to make search on ciphertexts without disclosing the information of encrypted messages and keywords. In practice, cryptographic operations often occur on insecure devices or mobile devices. But, these devices face the risk of being lost or stolen. Therefore, the secret keys stored on these devices are likely to be exposed. To handle the key exposure problem in PEKS, the notion of key-updatable PEKS (KU-PEKS) was proposed recently. In KU-PEKS, the users' keys can be updated as the system runs. Nevertheless, the existing KU-PEKS framework has some weaknesses. Firstly, it can't update the keyword ciphertexts on the storage server without leaking keyword information. Secondly, it needs to send the search tokens to the storage server by secure channels. Thirdly, it does not consider the search token security. In this work, a new PEKS framework named key-updatable and ciphertext-sharable PEKS (KU-CS-PEKS) is devised. This novel framework effectively overcomes the weaknesses in KU-PEKS and has the ciphertext sharing function which is not supported by KU-PEKS. The security notions for KU-CS-PEKS are formally defined and then a concrete KU-CS-PEKS scheme is proposed. The security proofs demonstrate that the KU-CS-PEKS scheme guarantees both the keyword ciphertext privacy and the search token privacy. The experimental results and comparisons bear out that the proposed scheme is practicable.

With the development of quantum computers, ring signature schemes based on large integer prime factorization, discrete logarithm problem, and bilinear pairing are under threat. For this reason, we design a ring signature scheme based on lattice with a fixed verification key. Compared with the previous ring signature scheme based on lattice, our design has a fixed verification key and does not disclose the signer's identity. Meanwhile, we propose an anonymous electronic voting scheme by using our ring signature scheme based on lattice and (t, n) threshold scheme, which makes up for the lack of current anonymous electronic voting that cannot resist attacks of the quantum computer. Finally, under standard model (SM), we prove that our ring signature scheme based on lattice is anonymous against the full-key exposure, and existentially non-forgeable against insider corruption. Furthermore, we also briefly analyze the security of our anonymous electronic voting scheme.

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.

In order to enhance system energy efficiency, bidirectional link resource allocation strategy in GFDM-based multiuser SWIPT systems is proposed. In the downlink channel, each SWIPT user applies power splitting (PS) receiver structure in information decoding (ID) and non-linear energy harvesting (EH). In the uplink channel, information transmission power is originated from the harvested energy. An optimization problem is constructed to maximize weighted sum ID achievable rates in the downlink and uplink channels via bidirectional link power allocation as well as subcarriers and subsymbols scheduling. To solve this non-convex optimization problem, Lagrange duality method, sub-gradient-based method and greedy algorithm are adopted respectively. Simulation results show that the proposed strategy is superior to the fixed subcarrier scheme regardless of the weighting coefficients. It is superior to the heuristic algorithm in larger weighting coefficients scenario.

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

Traditionally, in multi-user multi-carrier systems, the neighboring subband will be gapped by one subcarrier, which is set as guard band to reduce multiple access interference (MAI) between neighboring subbands. The empty subcarrier for guard band will degrade the spectral efficiency of the whole system. In order to enhance the spectral efficiency of multi-user filter bank multiple carrier (FBMC) systems, a new subband allocation method is introduced, in which the neighboring subband is gapped by half subcarrier instead of one subcarrier. Meanwhile, in order to implement the proposed resource allocation scheme, an optimized FBMC prototype filter is designed to decrease the inter-subband interference to the neighboring subband. The detailed simulations about the comparison between the proposed spectrum assignment and traditional FBMC are given, as well as the performance in the different interference scenarios. The simulation results show that the combination of the proposed spectrum assignment scheme and the optimized filter has better performance compared to the traditional scheme. The proposed scheme can be used in the system which serves massive users to get higher spectrum efficiency.