Jianyong Duan, Yadi Song, Yongmei Zhang, Mingli Wu, Hao Wang
Query recommendation plays an important role in improving users' search experience. Traditional ways most mine recommended words from log information. However, in user logs, sessions are difficult to divide. At the same time, click results are with bias and noise, and many queries lack clicks, it will make useful information be sparse. In this paper, we present a novel method based on local documents. Different from the traditional query recommendation, this method recommends related terminology according to the meaning of the query. We extract terminology documents from the pseudo-related feedback documents, then model topics of the terminology documents and use the inference strategies to infer the topic of the query to solve the problem of theme drift. In addition, to bring better recommendation results, we fuse supervised and unsupervised methods to mine semantic concept relations between query words and recommended words. Finally, the words with semantic concepts relation are recommended to the user. Experimental results show that our method can meet the user's search needs better. Compared with traditional query recommendation, users prefer the query recommendation way that we propose.
{"title":"Query Recommendation Using Topic Modeling and Word Embeddings","authors":"Jianyong Duan, Yadi Song, Yongmei Zhang, Mingli Wu, Hao Wang","doi":"10.1145/3268866.3268873","DOIUrl":"https://doi.org/10.1145/3268866.3268873","url":null,"abstract":"Query recommendation plays an important role in improving users' search experience. Traditional ways most mine recommended words from log information. However, in user logs, sessions are difficult to divide. At the same time, click results are with bias and noise, and many queries lack clicks, it will make useful information be sparse. In this paper, we present a novel method based on local documents. Different from the traditional query recommendation, this method recommends related terminology according to the meaning of the query. We extract terminology documents from the pseudo-related feedback documents, then model topics of the terminology documents and use the inference strategies to infer the topic of the query to solve the problem of theme drift. In addition, to bring better recommendation results, we fuse supervised and unsupervised methods to mine semantic concept relations between query words and recommended words. Finally, the words with semantic concepts relation are recommended to the user. Experimental results show that our method can meet the user's search needs better. Compared with traditional query recommendation, users prefer the query recommendation way that we propose.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123035929","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}
In this work, we propose an approach based on combinatorial optimization technique for Arabic word recognition that has been a challenge because of the significant topological variability and the complex inflectional nature of Arabic language. We handle a wide vocabulary of Arabic decomposable words, which we have decided to structure as a molecular cloud. This design rhymes well with the Arabic linguistic philosophy of constructing words around roots. Each sub-cloud includes neighboring words that derive from the same root and follow different forms of derivation, flexion, and agglutination (proclitic and enclitic). Thereby, we propose -as a recognition approach- to use on this enormous cloud, the technique of simulated annealing. Its algorithm is based on an elastic comparison between sequences of structural primitives. Preliminary experiments are carried on Arabic word corpus including samples from APTI database and first results are promising.
{"title":"Combinatorial Optimization Approach for Arabic Word Recognition","authors":"Zouaoui Zeineb, Ben Chiekh Imen, Jemni Mohamed","doi":"10.1145/3268866.3268884","DOIUrl":"https://doi.org/10.1145/3268866.3268884","url":null,"abstract":"In this work, we propose an approach based on combinatorial optimization technique for Arabic word recognition that has been a challenge because of the significant topological variability and the complex inflectional nature of Arabic language. We handle a wide vocabulary of Arabic decomposable words, which we have decided to structure as a molecular cloud. This design rhymes well with the Arabic linguistic philosophy of constructing words around roots. Each sub-cloud includes neighboring words that derive from the same root and follow different forms of derivation, flexion, and agglutination (proclitic and enclitic). Thereby, we propose -as a recognition approach- to use on this enormous cloud, the technique of simulated annealing. Its algorithm is based on an elastic comparison between sequences of structural primitives. Preliminary experiments are carried on Arabic word corpus including samples from APTI database and first results are promising.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114859503","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}
Efficient processing of digital images is a key consideration in many machine vision tasks. Traditional image processing approaches often struggle to meet this demand, particularly at the initial low-level of processing image pixels. To overcome this, we propose a spiral based processing approach which takes inspiration from the asymmetric lattice of interlocking cells found in the human visual system. Here we demonstrate the efficiency of the proposed spiral approach for multi-scale feature extraction. This is complemented by a biologically inspired image acquisition process which is used to capture nine image frames at different spatial locations. The results demonstrate that the biologically inspired spiral approach offers a faster alternative to corresponding traditional image processing approaches.
{"title":"Fast, Multi-Scale Image Processing on a Square Spiral Framework","authors":"J. Fegan, S. Coleman, D. Kerr, B. Scotney","doi":"10.1145/3268866.3268882","DOIUrl":"https://doi.org/10.1145/3268866.3268882","url":null,"abstract":"Efficient processing of digital images is a key consideration in many machine vision tasks. Traditional image processing approaches often struggle to meet this demand, particularly at the initial low-level of processing image pixels. To overcome this, we propose a spiral based processing approach which takes inspiration from the asymmetric lattice of interlocking cells found in the human visual system. Here we demonstrate the efficiency of the proposed spiral approach for multi-scale feature extraction. This is complemented by a biologically inspired image acquisition process which is used to capture nine image frames at different spatial locations. The results demonstrate that the biologically inspired spiral approach offers a faster alternative to corresponding traditional image processing approaches.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127244971","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}
The fast increase in the availability of weather data from various sensors and weather stations allows weather data mining to achieve much higher accuracy over time, serving for important economic and socioeconomic purposes. However, the availability and sparsity of weather data differs drastically for geologically separated locations and there exists wide across domain differences for different sources, resulting in various accuracy in predicting the weather for target locations with different weather patterns. This paper applies domain adaptation approach for weather classification, where a system is trained from one source domain but deployed on another target domain. This methodology outperforms other two alternative methods, showing lower misclassification rate than using only target domain or naïve combination of both target and source domain ignoring cross-domain differences. This work provides a framework for future weather data mining and encourages the domain adaptation approach in other applications in data mining with wide cross-domain differences in general.
{"title":"Application of Domain Adaptation Approach for Weather Data Mining","authors":"Yang Wang, Yuanzhe Shi","doi":"10.1145/3268866.3268879","DOIUrl":"https://doi.org/10.1145/3268866.3268879","url":null,"abstract":"The fast increase in the availability of weather data from various sensors and weather stations allows weather data mining to achieve much higher accuracy over time, serving for important economic and socioeconomic purposes. However, the availability and sparsity of weather data differs drastically for geologically separated locations and there exists wide across domain differences for different sources, resulting in various accuracy in predicting the weather for target locations with different weather patterns. This paper applies domain adaptation approach for weather classification, where a system is trained from one source domain but deployed on another target domain. This methodology outperforms other two alternative methods, showing lower misclassification rate than using only target domain or naïve combination of both target and source domain ignoring cross-domain differences. This work provides a framework for future weather data mining and encourages the domain adaptation approach in other applications in data mining with wide cross-domain differences in general.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114473022","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}
This paper presents an efficient approach to corner detection for images using a spiral addressing scheme in conjunction with simulated, biological involuntary eye movements. As part of this approach, a combined gradient detection and smoothing operation is used to quickly obtain a feature representation that can be used with a standard 'cornerness' measure. A computationally efficient use of a spiral address scheme to apply further processing operations such as non-maximum suppression is demonstrated. An evaluation of three corner detection methods is presented and results demonstrate that a method designed for a spiral based, biologically inspired approach can achieve a significantly faster runtime than comparative methods designed for a traditional approach.
{"title":"Fast, Biologically Inspired Corner Detection Using a Square Spiral Address Scheme and Artificial Eye Tremor","authors":"J. Fegan, S. Coleman, D. Kerr, B. Scotney","doi":"10.1145/3268866.3268883","DOIUrl":"https://doi.org/10.1145/3268866.3268883","url":null,"abstract":"This paper presents an efficient approach to corner detection for images using a spiral addressing scheme in conjunction with simulated, biological involuntary eye movements. As part of this approach, a combined gradient detection and smoothing operation is used to quickly obtain a feature representation that can be used with a standard 'cornerness' measure. A computationally efficient use of a spiral address scheme to apply further processing operations such as non-maximum suppression is demonstrated. An evaluation of three corner detection methods is presented and results demonstrate that a method designed for a spiral based, biologically inspired approach can achieve a significantly faster runtime than comparative methods designed for a traditional approach.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"278 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134184325","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}
This paper describes a general windowing method to improve the channel estimation of ultra-wideband communication systems, then proposes a new low-complexity channel estimation algorithm which can effectively resist the inter-symbol interference. The algorithm can resist the inter-symbol interference caused by the channel impulse response. The algorithm only requires a 32-point FFT module. It is verified that the algorithm can effectively reduce the interference caused by multi-path channel and noise.
{"title":"A Low Complexity FFT-based Algorithm for Channel Estimation of Ultra-Wideband Communication Systems","authors":"Zhixing Wang, Xinghua Ren, Z. Tan","doi":"10.1145/3268866.3268875","DOIUrl":"https://doi.org/10.1145/3268866.3268875","url":null,"abstract":"This paper describes a general windowing method to improve the channel estimation of ultra-wideband communication systems, then proposes a new low-complexity channel estimation algorithm which can effectively resist the inter-symbol interference. The algorithm can resist the inter-symbol interference caused by the channel impulse response. The algorithm only requires a 32-point FFT module. It is verified that the algorithm can effectively reduce the interference caused by multi-path channel and noise.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134221100","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}
Kidney medical image segmentation is the key step of medical image analysis and non-invasive computer aided diagnosis system in related kidney diseases. Based on the traditional Chan-Vese model, according to the continuity and redundancy of the kidney tissues between slices in the CT sequence images, combined with local statistical information for improving the curve evolution, combined with the initial contour based on a narrowband evolution curve and the termination conditions by using the biological continuity of adjacent slices, a kidney tissue segmentation model based on energy minimization was proposed. The model was used to process the 24 sets of standard segmentation test data sets. The segmentation results showed that the average PRA and DSC indices have improved over traditional models, reached 0.961 and 94.68%, respectively, the kidney tissue could be located and segmented efficiently and accurately.
{"title":"Method of Kidney Image Segmentation Based on Improved C-V Model","authors":"Hui Yu, Jian Jiao, Yuzhen Cao","doi":"10.1145/3268866.3268867","DOIUrl":"https://doi.org/10.1145/3268866.3268867","url":null,"abstract":"Kidney medical image segmentation is the key step of medical image analysis and non-invasive computer aided diagnosis system in related kidney diseases. Based on the traditional Chan-Vese model, according to the continuity and redundancy of the kidney tissues between slices in the CT sequence images, combined with local statistical information for improving the curve evolution, combined with the initial contour based on a narrowband evolution curve and the termination conditions by using the biological continuity of adjacent slices, a kidney tissue segmentation model based on energy minimization was proposed. The model was used to process the 24 sets of standard segmentation test data sets. The segmentation results showed that the average PRA and DSC indices have improved over traditional models, reached 0.961 and 94.68%, respectively, the kidney tissue could be located and segmented efficiently and accurately.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123450596","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}
With the continuous development of science and technology and the increasing frequency of information communication, the original data processing technology has been unable to suit to the development of the era. With the coming of the times of big data, the collection, analysis and utilization of multi data is becoming more and more important. The development of corresponding statistical work has also received more attention. In the new era of economic development, enterprises that occupy the advantage of information resources can get greater development. This paper will make a brief analysis of the research on the application feasibility of data mining technology.
{"title":"Research on the Application Feasibility of Data Mining Technology","authors":"Zhang Cheng-zhao","doi":"10.1145/3268866.3268878","DOIUrl":"https://doi.org/10.1145/3268866.3268878","url":null,"abstract":"With the continuous development of science and technology and the increasing frequency of information communication, the original data processing technology has been unable to suit to the development of the era. With the coming of the times of big data, the collection, analysis and utilization of multi data is becoming more and more important. The development of corresponding statistical work has also received more attention. In the new era of economic development, enterprises that occupy the advantage of information resources can get greater development. This paper will make a brief analysis of the research on the application feasibility of data mining technology.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129006320","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}
The vast majority of indoor navigation algorithms either rely on manual scene augmentation and labelling or exploit multi-sensor fusion techniques in achieving simultaneous localization and mapping (SLAM), leading to high computational costs, hardware complexities and robustness deficiencies. This paper proposes an efficient and robust deep learning-based indoor navigation framework for robots. Firstly, we put forward an end-to-end trainable siamese deep convolutional neural network (DCNN) which decomposes navigation into orientation and localization in one branch, while achieving semantic scene mapping in another. In mitigating the computational costs associated with DCNNs, the proposed model design shares a significant amount of convolutional operations between the two branches, streamlining the model and optimizing for efficiency in terms of memory and inference latency. Secondly, a transfer learning regime is explored in demonstrating how such siamese DCNNs can be efficiently trained for high convergence rates without extensive manual dataset labelling. The resulting siamese framework combines semantic scene understanding with orientation estimation towards predicting collision-free and optimal navigation paths. Experimental results demonstrate that the proposed framework achieves accurate and efficient navigation and outperforms existing "navigation-by-classification" variants.
{"title":"Autonomous Indoor Robot Navigation via Siamese Deep Convolutional Neural Network","authors":"Yao Yeboah, Cai Yanguang, W. Wu, Shuai He","doi":"10.1145/3268866.3268886","DOIUrl":"https://doi.org/10.1145/3268866.3268886","url":null,"abstract":"The vast majority of indoor navigation algorithms either rely on manual scene augmentation and labelling or exploit multi-sensor fusion techniques in achieving simultaneous localization and mapping (SLAM), leading to high computational costs, hardware complexities and robustness deficiencies. This paper proposes an efficient and robust deep learning-based indoor navigation framework for robots. Firstly, we put forward an end-to-end trainable siamese deep convolutional neural network (DCNN) which decomposes navigation into orientation and localization in one branch, while achieving semantic scene mapping in another. In mitigating the computational costs associated with DCNNs, the proposed model design shares a significant amount of convolutional operations between the two branches, streamlining the model and optimizing for efficiency in terms of memory and inference latency. Secondly, a transfer learning regime is explored in demonstrating how such siamese DCNNs can be efficiently trained for high convergence rates without extensive manual dataset labelling. The resulting siamese framework combines semantic scene understanding with orientation estimation towards predicting collision-free and optimal navigation paths. Experimental results demonstrate that the proposed framework achieves accurate and efficient navigation and outperforms existing \"navigation-by-classification\" variants.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"224 14","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114096936","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}
CF (Collaborative filtering) algorithm has the widest and most successful applications in personalized recommendations. However, due to its over-reliance on the users' historical data, it is difficult to avoid data sparseness and cold start issues. The data sparseness and cold start may cause poor recommendation accuracy of the collaborative filtering algorithm. A hybrid optimal collaborative filtering algorithm based on users' characteristics and trust is proposed in this paper. In the process of users' similarity calculation, the age and gender of users' characteristics are introduced to make the determination of nearest neighbor more accurate. Besides, in order to improve the recommendation accuracy of the traditional CF recommendation algorithm, the trust relationship is introduced into the prediction score by measuring the users' trust, and this improvement will be used in the recommendation of new items in order to improve the recommendation accuracy of the traditional CF recommendation algorithm. The experimental results of Movie lens data set show that the improved recommendation accuracy of the recommendation system can be achieved by the proposed algorithm. Also, the problems of cold start and sparse data can be solved effectively.
{"title":"Optimized CF Recommendation Algorithm Based on Users' Characteristics and Trust","authors":"Q. Jin, Xia Song, Ming-Hua Yang, Wu Cai","doi":"10.1145/3268866.3268887","DOIUrl":"https://doi.org/10.1145/3268866.3268887","url":null,"abstract":"CF (Collaborative filtering) algorithm has the widest and most successful applications in personalized recommendations. However, due to its over-reliance on the users' historical data, it is difficult to avoid data sparseness and cold start issues. The data sparseness and cold start may cause poor recommendation accuracy of the collaborative filtering algorithm. A hybrid optimal collaborative filtering algorithm based on users' characteristics and trust is proposed in this paper. In the process of users' similarity calculation, the age and gender of users' characteristics are introduced to make the determination of nearest neighbor more accurate. Besides, in order to improve the recommendation accuracy of the traditional CF recommendation algorithm, the trust relationship is introduced into the prediction score by measuring the users' trust, and this improvement will be used in the recommendation of new items in order to improve the recommendation accuracy of the traditional CF recommendation algorithm. The experimental results of Movie lens data set show that the improved recommendation accuracy of the recommendation system can be achieved by the proposed algorithm. Also, the problems of cold start and sparse data can be solved effectively.","PeriodicalId":285628,"journal":{"name":"Proceedings of the 2018 International Conference on Artificial Intelligence and Pattern Recognition","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128190772","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：