2022 International Conference on Networking and Network Applications (NaNA)最新文献

{"title":"Bioacoustics Monitoring of Wildlife using Artificial Intelligence: A Methodological Literature Review","authors":"Sandhya Sharma, Kazuhiko Sato, B. P. Gautam","doi":"10.1109/NaNA56854.2022.00063","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00063","url":null,"abstract":"Artificial intelligence (AI) is a broad computing science that has attracted significant attention in the ecological sector because of its problem-solving, deciding, and pattern recognition capabilities. Because of the large number of datasets available across spatiotemporal scales that may be used for machine learning and interpretation, bioacoustics wildlife monitoring is essential in the performance of AI techniques. Although several studies have enforced AI algorithms into the wildlife ecology, the future of this developing method in wildlife acoustic monitoring is unknown. In this study, we performed a scientific literature review covering 20 papers from 2015 and March 2022 to evaluate its application and advise future demands. During this time, we observed a considerable increase in the use of AI approaches in wildlife acoustic monitoring. Overall, bird species $(mathbf{N}=mathbf{12})$ received the most attention, followed by amphibians $(mathbf{N}=mathbf{5})$ and mammals $(mathbf{N}=mathbf{3})$), even though their operations are diversifying. Among the AI learnings used in bioacoustics wildlife monitoring, a convolutional neural network was highly accurate in terms of performance, had more advantages, and was replicated in multiple articles than other classification methods. Reviewing previously used AI algorithms in bioacoustics research is expected to aid in understanding the trends and identifying gaps in automatic wildlife monitoring.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125055237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Identifying Those Who Really Need Subsidies: A Data-Driven Approach","authors":"Chunyan Yu, Linfeng Gu, Guilin Chen, Aiguo Wang","doi":"10.1109/NaNA56854.2022.00071","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00071","url":null,"abstract":"Subsidies and supportive policies have been often offered by universities to students with financial difficulties. However, it is a non-trivial task to scientifically and accurately identify students who really need subsidies with the traditional apply-review method. In a smart campus, students use a campus card to spend money on affairs such as eating in the canteen, taking a bath, and shopping in the supermarket for their daily living, and the consumption records potentially reflect the economic level and the living habits of students. To this end, we herein propose a data-driven approach that combines statistical methods and machine learning models (CSML) to accurately identify students who really need financial aid. CSML first preprocesses the consumption data and extracts seven informative features that are closely related to eating and bath charges. Second, the overall consumption portraits of different gender, grade, and financial difficulty levels are obtained, and false poverty and suspected poverty students are excluded from the study based on the average consumption. Third, a supervised classification model is used to predict the type of financial difficulties a student belongs to, followed by a statistical method to check whether the student predicted with financial difficulties spends more. Experiment results show that CSML achieves a 96% precision in identifying students with financial difficulties, which reveals the power of CSML in helping evaluate the effect of subsidies.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114901824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimization Model for Predicting Stored Grain Temperature Using Deep Learning LSTMs","authors":"Koomson Patrick, Weidong Yang, Erbo Shen","doi":"10.1109/NaNA56854.2022.00068","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00068","url":null,"abstract":"With reliable and accurate grain temperature forecasting models, granary operators could easily make the right decisions to avoid food spoilage. In this study, an analysis of a single hidden layer long short-term memory model, a multi-layer (stacked) long short-term memory model, and its evaluation is presented to determine how accurate it is for forecasting stored grain's temperature from past data. Using temperature sensors, the data is collected over three years in a warehouse in Yunnan, China. There are two datasets: a training dataset and a test dataset. About 40 percent of the data is set aside as a test dataset, while the remaining 60 percent is used as a training dataset. There are several hyper-parameters included in the analysis. By computing the root of the mean square error (RMSE), we can compare the two models. We also use the mean absolute error assessment tool (MAE) and the correlation between predicted and actual values (R2) to evaluate the prediction. In addition to optimizing the number of hidden layers and neurons in each hidden layer, the two models are improved by comparing the actual and predicted models. The experiments we conducted confirm that a single hidden layer can achieve the same or better results than the multilayer (stacked) LSTM when the hyper-parameters are chosen and tuned appropriately, considering the size of the data and the goal.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"384 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116225558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Load balancing strategy for wireless multi-hotspot networks based on improved NSGA-II algorithm","authors":"Han Yu, Jie Zhan, Libin Jiao, Junmei Han","doi":"10.1109/NaNA56854.2022.00026","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00026","url":null,"abstract":"IEEE 802.11 Wireless Local Area Network (WLAN) is a popular way for mobile devices to access the Internet. Operators and service providers often increase the density of wireless access points in order to provide users with better connections and user experience. As a result, WLAN users find themselves covered by multiple access points. In traditional wireless multi-hotspot networks most user terminals choose the access point with the strongest signal without considering the existing load on that access point, leading to severe congestion and load imbalance problems. This paper proposes an improved NSGA-II-based load balancing strategy for wireless multi-hotspot networks, which determines which hotspot should be associated with each user terminal by taking into account the current access point load, the received signal strength and the throughput size of the user terminal. The simulation results show that compared with the traditional strongest signal First (SSF) strategy, the proposed load balancing strategy can improve the network throughput by more than 30%.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114044653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Feature-level Attention Pooling for Overlapping Sound Event Detection","authors":"Mei Wang, Zhengyi An, Yuh-Lin Yao, Xiyu Song","doi":"10.1109/NaNA56854.2022.00098","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00098","url":null,"abstract":"The aim of overlapping sound event detection (SED) is to detect the sound events classes contained and the corresponding time stamps in audio. In real life, the sound events contained in a piece of audio are usually very complicated, and various sound events overlap and alternate, which greatly increases the difficulty of overlapping SED. In our past research, we found that the attention mechanism can effectively cope with the mentioned difficulty, as long as its need for reinforcement training on a large amount of strongly labeled data is satisfied. However, strongly labeled data is usually not easy to obtain, so how to use weakly labeled data has become mainstream. Against this background, we propose a new overlapping SED method that can effectively utilize weakly labeled data through the use of the feature-level attention pooling strategy under the multiple-instance learning (MIL) framework. Moreover, a feature-level attention pooling strategy with different learnable parameters is studied and compared with a decision-level attention pooling strategy in our work, so the advantages of attention with a feature-level attention pooling strategy in overlapping SED can be better shown. We compare the classification results of overlapping SED using feature-level and decision-level attention pooling in the DCASE 2021 task 4 scenario (Sound Event Detection and Separation in Domestic Environments). Test results show that the PSDS1 (focus on the sensitiveness to the detection speed) of feature-level attention pooling is kept unchanged (it means the learnable parameters training does not burden the overlapping SED), but the PSDS2 (focus on the classification effect) is improved by 3%, which is slightly above the score generated from the decision-level attention pooling (it means feature-level attention pooling has better returns). Although the results are only slightly improved when compared to the decision-level attention pooling, it has somehow improved research guidance for the research of improving the classification results of overlapping SED. Our conclusion is that feature-level attention pooling is good for exploiting weak-label data, and can achieve better classification without increasing computational complexity.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117252995","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Short Text Semantic Matching Model based on Bert and Adversarial Network","authors":"T. Zhang, Zhe Zhang, Xiang Li, Yulin Wu, Bo Peng, Yurong Qian, Mengnan Ma, Hongyong Leng","doi":"10.1109/NaNA56854.2022.00073","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00073","url":null,"abstract":"Short text semantic matching plays an important role in the fields of natural language processing such as fast retrieval, intelligent question answering, and information matching. Aiming at the problem of word polysemy that is difficult to solve by conventional models, this paper proposes a short text semantic matching model BERT-GAN based on the BERT (Bidirectional Encoder Representations from Transformers) pre-training model and combined with the adversarial network in the fine-tuning stage. The basic idea is as follows: Using BERT to extract text features, and then introducing an adversarial network in the fine-tuning stage of the task to add perturbation to the embedding layer to improve the generalization ability and robustness of the model. The experimental results show that the BERT-GAN short text semantic matching model is better than the comparison model, and the F1 value is improved by 10.5%, 6.6% and 0.9% respectively compared with the comparison model.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124550934","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ADN: ATSS-based Deep Network for Pedestrian Detection on High-Resolution Images","authors":"Wang Mo, Yan Ke, Qingao Huo, Ruyi Cao, Guochang Song, Wendong Zhang","doi":"10.1109/NaNA56854.2022.00084","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00084","url":null,"abstract":"This paper investigates the high-resolution pedestrian detection network AND(ATSS-based Deep Network for Pedestrian Detection on High-Resolution Images) to solve the problem that high-resolution images are difficult to be processed directly as well as pedestrian occlusion and pose variations. First, it obtains a deeper backbone network by stacking residual modules to extract multi-level features, improve the extraction ability of occluded target features and avoid network degradation. Subsequently, the deformable convolution is introduced to optimize the backbone network and expand the local receptive field, thus further optimizing the detection ability of deformable targets and occluded targets. On the PANDA dataset, the AP, AP50, and AP75 of ADN are 3.5, 2.7, and 4.2, which are higher than that for the baseline respectively. Compared with other state-of-the-art methods, experiments show that ADN effectively enhances the accuracy of pedestrian detection in high-resolution Imgaes, and it outperforms existing object detection algorithms.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127908242","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multivariate-aided Power-consumption Prediction Based on LSTM-Kalman Filter","authors":"Shuai Lyu, Haoran Mei, Limei Peng, Shih Yu Chang, Jian Mo","doi":"10.1109/NaNA56854.2022.00100","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00100","url":null,"abstract":"Forecasting the power consumption of home appli-ances on a time-series basis is significant in monitoring and predicting daily human behaviors. On the other hand, time-series forecasting is challenged by the uncertain and complex external environment, such as weather conditions that affect prediction accuracy. A promising method to improve the prediction accuracy is to adopt multiple external environment variables. Regarding this, the paper proposes using the multivariate dataset and the Kalman filter (KF) to predict the electrical power consumed by the smart home appliance. We conduct extensive experiments based on the real datasets of power consumption, which are classified into multivariate and univariate and used in the LSTM-KF model to predict the power consumption of the smart home appliance. The LSTM here stores the data information for static prediction, and the Kalman filter dynamically adjusts the prediction results to obtain a final prediction value. The LSTM-KF models applying the proposed multivariate and the univariate are compared in terms of the RMSE and the determination coefficient R2. The LSTM - KF using multivariate shows the best accuracy. Nonetheless, the univariate method using the Kalman filter outperforms the multivariate method without using the Kalman filter, implying the significance of using multiple variables together with the Kalman filter in improving the prediction accuracy.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133077305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An efficient method for restraining negative information cascades in online social networks","authors":"Yan Wang, Li Li, ZhaoHua Wang, Xiaohua Zheng","doi":"10.1109/NaNA56854.2022.00085","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00085","url":null,"abstract":"Information cascades is recognized as a major factor in disastrous social network phenomenons. The clustering of network community can block the cascade of negative information and users' behaviors in online social networks (OSNs). Confronting limited network resources, this paper takes the interaction relationship between network structure optimizing and neighbors' behaviors cascading as the breakthrough point, and study the restrain method of negative information cascades under emergency. This paper proposes a method for restraining the cascade of negative information, which is in order to improve the clustering of network communities by means of links that are logically removed (termed CLLR). By limited links with high betweenness being logically removed, CLLR method enhances the community density in a network, thereby effectively block information cascades. Experimental results show that CLLR method significantly improve the clustering of a network, efficiently block the speed and scope of information cascades in OSNs.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131283833","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hey! You Photographed My Screen without Approved: A Practical Screen Content Protection Scheme Based on Visual Cryptography","authors":"Kui Liu, Bin Wang, Ziwei Shi, Jiadong Chen, Zhiwei Zhang","doi":"10.1109/NaNA56854.2022.00069","DOIUrl":"https://doi.org/10.1109/NaNA56854.2022.00069","url":null,"abstract":"Nowadays , with the continuous development of digital media, electronic screens have become the most direct tool for people to interact with information. Various styles of electronic screens provide vivid information exchange methods for people's lives, and at the same time make information leakage more likely to happen. Electronic screens are susceptible to stealing photographs when sharing information, which leads to information leakage and security issues. Under the unavoidable situation of such leaks, various protection schemes have been proposed before, but these schemes cannot effectively protect the screen content. Therefore, in this paper, we propose an effective a screen content protection scheme, based on Visual Cryptography(VC) for image encryption, combined with Scale-Invariant Feature Transform(SIFT) to deal with screen stealing scenes. In addition, our experiments show that our scheme is superior to existing schemes in terms of convenience and security.","PeriodicalId":113743,"journal":{"name":"2022 International Conference on Networking and Network Applications (NaNA)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115843245","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}