Pub Date : 2021-03-01DOI: 10.4018/IJDCF.2021030103
Rohit M. Thanki, Surekha Borra, A. Kothari
Application of fragile watermarking on biometric images stored at a server or cloud ensures proper authentication and tamper detection when access to the servers was shared. In this paper, a hybrid domain fragile watermarking technique for authenticity of color biometric images, using hybridization of various transforms such as discrete cosine transform (DCT), fast discrete curvelet transform (FDCuT), and singular value decomposition (SVD) is proposed. The hybrid transform coefficients are modified according to the scrambled color watermark to obtain watermarked color biometric image. The security of this technique is strengthened with the usage of Arnold scrambling, and by using multiple secret keys. The proposed technique is analyzed on FEI Brazilian face database. The experimental results show that this technique performs better than the existing fragile watermarking techniques.
{"title":"Fragile Watermarking Framework for Tamper Detection of Color Biometric Images","authors":"Rohit M. Thanki, Surekha Borra, A. Kothari","doi":"10.4018/IJDCF.2021030103","DOIUrl":"https://doi.org/10.4018/IJDCF.2021030103","url":null,"abstract":"Application of fragile watermarking on biometric images stored at a server or cloud ensures proper authentication and tamper detection when access to the servers was shared. In this paper, a hybrid domain fragile watermarking technique for authenticity of color biometric images, using hybridization of various transforms such as discrete cosine transform (DCT), fast discrete curvelet transform (FDCuT), and singular value decomposition (SVD) is proposed. The hybrid transform coefficients are modified according to the scrambled color watermark to obtain watermarked color biometric image. The security of this technique is strengthened with the usage of Arnold scrambling, and by using multiple secret keys. The proposed technique is analyzed on FEI Brazilian face database. The experimental results show that this technique performs better than the existing fragile watermarking techniques.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"122 1","pages":"35-56"},"PeriodicalIF":0.7,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79463067","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}
Pub Date : 2021-01-01DOI: 10.4018/ijdcf.2021010102
Jyotismita Chaki, N. Dey
Palmprint recognition has been comprehensively examined in the past couple of years and various undertakings are done to use it as a biometric methodology for various applications. The point of this study is to construct an effective palmprint recognition technique with low computational multifaceted nature and along these lines to expand the acknowledgment and precision. Since edges are free from distortion, they are very reliable and subsequently used for palm print recognition. The originality of the proposed technique depends on new area of interest (ROI) extraction took after by new principal line extraction and texture matching strategy. The new principal line extraction technique is created by using the Hessian matrix and Eigen value. The texture matching of the ROI is done using new 2-component partition method by segmenting the image into comparative and non-comparative edges. Examinations are finished on a database and exploratory results exhibit that the accuracy of the proposed method is comparable to past methods used for palmprint recognition.
{"title":"Palmprint Recognition Using Hessian Matrix and Two-Component Partition Method","authors":"Jyotismita Chaki, N. Dey","doi":"10.4018/ijdcf.2021010102","DOIUrl":"https://doi.org/10.4018/ijdcf.2021010102","url":null,"abstract":"Palmprint recognition has been comprehensively examined in the past couple of years and various undertakings are done to use it as a biometric methodology for various applications. The point of this study is to construct an effective palmprint recognition technique with low computational multifaceted nature and along these lines to expand the acknowledgment and precision. Since edges are free from distortion, they are very reliable and subsequently used for palm print recognition. The originality of the proposed technique depends on new area of interest (ROI) extraction took after by new principal line extraction and texture matching strategy. The new principal line extraction technique is created by using the Hessian matrix and Eigen value. The texture matching of the ROI is done using new 2-component partition method by segmenting the image into comparative and non-comparative edges. Examinations are finished on a database and exploratory results exhibit that the accuracy of the proposed method is comparable to past methods used for palmprint recognition.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"14 1","pages":"26-47"},"PeriodicalIF":0.7,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87349765","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}
Pub Date : 2021-01-01DOI: 10.4018/ijdcf.2021010105
R. Mittal, M. P. S. Bhatia
In this age, where cryptocurrencies are slowly creeping into the banking services and making a name for them, it is becoming crucially essential to figure out the security concerns when users make transactions. This paper investigates the untrusted users of cryptocurrency transaction services, which are connected using smartphones and computers. However, as technology is increasing, transaction frauds are growing, and there is a need to detect vulnerabilities in systems. A methodology is proposed to identify suspicious users based on their reputation score by collaborating centrality measures and machine learning techniques. The results are validated on two cryptocurrencies network datasets, Bitcoin-OTC, and Bitcoin-Alpha, which contain information of the system formed by the users and the user's trust score. Results found that the proposed approach provides improved and accurate results. Hence, the fusion of machine learning with centrality measures provides a highly robust system and can be adapted to prevent smart devices' financial services.
{"title":"Detection of Suspicious or Un-Trusted Users in Crypto-Currency Financial Trading Applications","authors":"R. Mittal, M. P. S. Bhatia","doi":"10.4018/ijdcf.2021010105","DOIUrl":"https://doi.org/10.4018/ijdcf.2021010105","url":null,"abstract":"In this age, where cryptocurrencies are slowly creeping into the banking services and making a name for them, it is becoming crucially essential to figure out the security concerns when users make transactions. This paper investigates the untrusted users of cryptocurrency transaction services, which are connected using smartphones and computers. However, as technology is increasing, transaction frauds are growing, and there is a need to detect vulnerabilities in systems. A methodology is proposed to identify suspicious users based on their reputation score by collaborating centrality measures and machine learning techniques. The results are validated on two cryptocurrencies network datasets, Bitcoin-OTC, and Bitcoin-Alpha, which contain information of the system formed by the users and the user's trust score. Results found that the proposed approach provides improved and accurate results. Hence, the fusion of machine learning with centrality measures provides a highly robust system and can be adapted to prevent smart devices' financial services.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"1 1","pages":"79-93"},"PeriodicalIF":0.7,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81902837","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}
Pub Date : 2021-01-01DOI: 10.4018/ijdcf.2021010104
A. Sahu, Ashish Kumar
The services of the internet play an essential part in the daily life of the users. So, safety and confidentiality of the information are to be maintained to preserve user conviction in various services offered by network. The two-factor-based password verification techniques are used between remote server and legitimate users for verification over insecure channel. Several protocols have been suggested previously claiming their simplicity, privacy, safety, and robustness. The authors proved that their enhanced protocols are vulnerable to different attacks on the network and permit only authenticated users to update their password preserving traceability and identity. Analysis shows that no scheme has fulfilled all the security requirements and achieved entire goals. Therefore, in this article, a scheme has been presented to overcome these issues in the previous schemes to resist illegal access leading to misuse and achieve all the security requirements and goals. The safety analysis of the presented scheme has confirmed its performance in terms of reliability and safety.
{"title":"A Novel Verification Protocol to Restrict Unconstitutional Access of Information From Smart Card","authors":"A. Sahu, Ashish Kumar","doi":"10.4018/ijdcf.2021010104","DOIUrl":"https://doi.org/10.4018/ijdcf.2021010104","url":null,"abstract":"The services of the internet play an essential part in the daily life of the users. So, safety and confidentiality of the information are to be maintained to preserve user conviction in various services offered by network. The two-factor-based password verification techniques are used between remote server and legitimate users for verification over insecure channel. Several protocols have been suggested previously claiming their simplicity, privacy, safety, and robustness. The authors proved that their enhanced protocols are vulnerable to different attacks on the network and permit only authenticated users to update their password preserving traceability and identity. Analysis shows that no scheme has fulfilled all the security requirements and achieved entire goals. Therefore, in this article, a scheme has been presented to overcome these issues in the previous schemes to resist illegal access leading to misuse and achieve all the security requirements and goals. The safety analysis of the presented scheme has confirmed its performance in terms of reliability and safety.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"287 1","pages":"65-78"},"PeriodicalIF":0.7,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77893946","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}
Pub Date : 2021-01-01DOI: 10.4018/ijdcf.2021010103
S. Yadav, Kavita Sharma, Ananya Gupta
The security of women is of prime concern around the world. Women feel insecure while traveling out of the home due to the fear of violence. The fear of violence restricts women's participating in different social activities. So instead of becoming a victim of a violent crime such as domestic violence, robbery, or rape, women should call on resources to help her out of that situation. In this paper, the authors develop a women safety device, namely SafeWomen, which helps in reducing the crimes held against women. This is a new approach for providing security to women in any unsafe situation by sending an alert having geographical location along with emergency message to the registered contact numbers so that the incident could be prevented. Also, it can track the current location of the victim just by knowing the IP address of the device she is using. One can also use this system for the safety and security of kids and elderly people just by making some changes in the functionality of the system.
{"title":"SafeWomen","authors":"S. Yadav, Kavita Sharma, Ananya Gupta","doi":"10.4018/ijdcf.2021010103","DOIUrl":"https://doi.org/10.4018/ijdcf.2021010103","url":null,"abstract":"The security of women is of prime concern around the world. Women feel insecure while traveling out of the home due to the fear of violence. The fear of violence restricts women's participating in different social activities. So instead of becoming a victim of a violent crime such as domestic violence, robbery, or rape, women should call on resources to help her out of that situation. In this paper, the authors develop a women safety device, namely SafeWomen, which helps in reducing the crimes held against women. This is a new approach for providing security to women in any unsafe situation by sending an alert having geographical location along with emergency message to the registered contact numbers so that the incident could be prevented. Also, it can track the current location of the victim just by knowing the IP address of the device she is using. One can also use this system for the safety and security of kids and elderly people just by making some changes in the functionality of the system.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"1 1","pages":""},"PeriodicalIF":0.7,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70454306","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}
Pub Date : 2021-01-01DOI: 10.4018/ijdcf.2021010101
Khalifa Al-Room, Farkhund Iqbal, T. Baker, B. Shah, Benjamin Yankson, Áine MacDermott, Patrick C. K. Hung
Drones (a.k.a. unmanned aerial vehicles – UAV) have become a societal norm in our daily lives. The ability of drones capture high-quality photos from an aerial view and store and transmit such data presents a multi-facet problem. These actions possess privacy challenges to innocent users who can be spied on or drone owner's data which may be intercepted by a hacker. With all technological paradigms, utilities can be misused, and this is an increasing occurrence with drones. As a result, it is imperative to develop a novel methodological approach for the digital forensic analysis of a seized drone. This paper investigates six brands of drones commonly used in criminal activities and extracts forensically relevant data such as location information, captured images and videos, drones' flight paths, and data related to the ownership of the confiscated drone. The experimental results indicate that drone forensics would facilitate law enforcement in collecting significant information necessary for criminal investigations.
{"title":"Drone Forensics: A Case Study of Digital Forensic Investigations Conducted on Common Drone Models","authors":"Khalifa Al-Room, Farkhund Iqbal, T. Baker, B. Shah, Benjamin Yankson, Áine MacDermott, Patrick C. K. Hung","doi":"10.4018/ijdcf.2021010101","DOIUrl":"https://doi.org/10.4018/ijdcf.2021010101","url":null,"abstract":"Drones (a.k.a. unmanned aerial vehicles – UAV) have become a societal norm in our daily lives. The ability of drones capture high-quality photos from an aerial view and store and transmit such data presents a multi-facet problem. These actions possess privacy challenges to innocent users who can be spied on or drone owner's data which may be intercepted by a hacker. With all technological paradigms, utilities can be misused, and this is an increasing occurrence with drones. As a result, it is imperative to develop a novel methodological approach for the digital forensic analysis of a seized drone. This paper investigates six brands of drones commonly used in criminal activities and extracts forensically relevant data such as location information, captured images and videos, drones' flight paths, and data related to the ownership of the confiscated drone. The experimental results indicate that drone forensics would facilitate law enforcement in collecting significant information necessary for criminal investigations.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"1 1","pages":"1-25"},"PeriodicalIF":0.7,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88717900","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}
Pub Date : 2020-10-01DOI: 10.4018/IJDCF.2020100102
Yang Zhao, Yaqin Fan, Mingrui Yin, Cheng Fang
With the promotion of online education, the adaptive learning system has attracted attention due to its good curriculum recommendation function. The student model is an important interface between the adaptive learning system and the user, reflecting the individual characteristics, knowledge status, and cognitive ability of the student. The accuracy of the information in the student model directly affects the quality of the system recommendation service. The traditional student model only judges students based on the basic information and simple test scores. This paper introduces the self-adaptive item bank and adaptive item selection strategy based on the cognitive diagnosis theory that dynamically detects the students' knowledge and analyzes the state according to the answering habits and knowledge mastering status of different students. This paper analyzes and contrasts a variety of traditional cognitive diagnosis theories and proposes a mixed cognitive diagnosis question bank and a selection strategy model to provide strong support for the construction of student models.
{"title":"Research on the Construction of a Student Model of an Adaptive Learning System Based on Cognitive Diagnosis Theory","authors":"Yang Zhao, Yaqin Fan, Mingrui Yin, Cheng Fang","doi":"10.4018/IJDCF.2020100102","DOIUrl":"https://doi.org/10.4018/IJDCF.2020100102","url":null,"abstract":"With the promotion of online education, the adaptive learning system has attracted attention due to its good curriculum recommendation function. The student model is an important interface between the adaptive learning system and the user, reflecting the individual characteristics, knowledge status, and cognitive ability of the student. The accuracy of the information in the student model directly affects the quality of the system recommendation service. The traditional student model only judges students based on the basic information and simple test scores. This paper introduces the self-adaptive item bank and adaptive item selection strategy based on the cognitive diagnosis theory that dynamically detects the students' knowledge and analyzes the state according to the answering habits and knowledge mastering status of different students. This paper analyzes and contrasts a variety of traditional cognitive diagnosis theories and proposes a mixed cognitive diagnosis question bank and a selection strategy model to provide strong support for the construction of student models.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"10 1","pages":"20-31"},"PeriodicalIF":0.7,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79211295","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}
Pub Date : 2020-10-01DOI: 10.4018/IJDCF.2020100101
Prathap Rudra Boppuru, Ramesha Kenchappa
In developing countries like India, crime plays a detrimental role in economic growth and prosperity. With the increase in delinquencies, law enforcement needs to deploy limited resources optimally to protect citizens. Data mining and predictive analytics provide the best options for the same. This paper examines the news feed data collected from various sources regarding crime in India and Bangalore city. The crimes are then classified on the geographic density and the crime patterns such as time of day to identify and visualize the distribution of national and regional crime such as theft, murder, alcoholism, assault, etc. In total, 68 types of crime-related dictionary keywords are classified into six classes based on the news feed data collected for one year. Kernel density estimation method is used to identify the hotspots of crime. With the help of the ARIMA model, time series prediction is performed on the data. The diversity of crime patterns is visualized in a customizable way with the help of a data mining platform.
{"title":"Spatio-Temporal Crime Analysis Using KDE and ARIMA Models in the Indian Context","authors":"Prathap Rudra Boppuru, Ramesha Kenchappa","doi":"10.4018/IJDCF.2020100101","DOIUrl":"https://doi.org/10.4018/IJDCF.2020100101","url":null,"abstract":"In developing countries like India, crime plays a detrimental role in economic growth and prosperity. With the increase in delinquencies, law enforcement needs to deploy limited resources optimally to protect citizens. Data mining and predictive analytics provide the best options for the same. This paper examines the news feed data collected from various sources regarding crime in India and Bangalore city. The crimes are then classified on the geographic density and the crime patterns such as time of day to identify and visualize the distribution of national and regional crime such as theft, murder, alcoholism, assault, etc. In total, 68 types of crime-related dictionary keywords are classified into six classes based on the news feed data collected for one year. Kernel density estimation method is used to identify the hotspots of crime. With the help of the ARIMA model, time series prediction is performed on the data. The diversity of crime patterns is visualized in a customizable way with the help of a data mining platform.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"25 1","pages":"1-19"},"PeriodicalIF":0.7,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83859766","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}
Pub Date : 2020-10-01DOI: 10.4018/IJDCF.2020100106
Xin Zheng, Jun Li, Qi Wu
Since the explosive growth of we-medias today, personalized recommendation is playing an increasingly important role to help users to find their target articles in vast amounts of data. Deep learning, on the other hand, has shown good results in image processing, computer vision, natural language processing, and other fields. But it's a relative blank in the application of we-media articles recommendation. Combining the new features of we-media articles, this paper puts forward a recommendation algorithm of we-media articles based on topic model, Latent Dirichlet Allocation (LDA), and deep learning algorithm, Recurrent Neural Networks (RNNs). Experiments on the real datasets show that the combined method outperforms the traditional collaborative filtering recommendation and non-personalized recommendation method.
{"title":"A Light Recommendation Algorithm of We-Media Articles Based on Content","authors":"Xin Zheng, Jun Li, Qi Wu","doi":"10.4018/IJDCF.2020100106","DOIUrl":"https://doi.org/10.4018/IJDCF.2020100106","url":null,"abstract":"Since the explosive growth of we-medias today, personalized recommendation is playing an increasingly important role to help users to find their target articles in vast amounts of data. Deep learning, on the other hand, has shown good results in image processing, computer vision, natural language processing, and other fields. But it's a relative blank in the application of we-media articles recommendation. Combining the new features of we-media articles, this paper puts forward a recommendation algorithm of we-media articles based on topic model, Latent Dirichlet Allocation (LDA), and deep learning algorithm, Recurrent Neural Networks (RNNs). Experiments on the real datasets show that the combined method outperforms the traditional collaborative filtering recommendation and non-personalized recommendation method.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"326 1","pages":"68-81"},"PeriodicalIF":0.7,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73122619","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}
Pub Date : 2020-10-01DOI: 10.4018/IJDCF.2020100103
Xin Liu, RuiHua Qi, Lin Shao
Intent determination (ID) and slot filling (SF) are two critical steps in the spoken language understanding (SLU) task. Conventionally, most previous work has been done for each subtask respectively. To exploit the dependencies between intent label and slot sequence, as well as deal with both tasks simultaneously, this paper proposes a joint model (ABLCJ), which is trained by a united loss function. In order to utilize both past and future input features efficiently, a joint model based Bi-LSTM with contextual information is employed to learn the representation of each step, which are shared by two tasks and the model. This paper also uses sentence-level tag information learned from a CRF layer to predict the tag of each slot. Meanwhile, a submodule-based attention is employed to capture global features of a sentence for intent classification. The experimental results demonstrate that ABLCJ achieves competitive performance in the Shared Task 4 of NLPCC 2018.
{"title":"Joint Model-Based Attention for Spoken Language Understanding Task","authors":"Xin Liu, RuiHua Qi, Lin Shao","doi":"10.4018/IJDCF.2020100103","DOIUrl":"https://doi.org/10.4018/IJDCF.2020100103","url":null,"abstract":"Intent determination (ID) and slot filling (SF) are two critical steps in the spoken language understanding (SLU) task. Conventionally, most previous work has been done for each subtask respectively. To exploit the dependencies between intent label and slot sequence, as well as deal with both tasks simultaneously, this paper proposes a joint model (ABLCJ), which is trained by a united loss function. In order to utilize both past and future input features efficiently, a joint model based Bi-LSTM with contextual information is employed to learn the representation of each step, which are shared by two tasks and the model. This paper also uses sentence-level tag information learned from a CRF layer to predict the tag of each slot. Meanwhile, a submodule-based attention is employed to capture global features of a sentence for intent classification. The experimental results demonstrate that ABLCJ achieves competitive performance in the Shared Task 4 of NLPCC 2018.","PeriodicalId":44650,"journal":{"name":"International Journal of Digital Crime and Forensics","volume":"23 1","pages":"32-43"},"PeriodicalIF":0.7,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73014436","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：