{"title":"An experimental analysis of DAG scheduling methods in hard real-time multiprocessor systems","authors":"Manar Qamhieh, Serge Midonnet","doi":"10.1145/2663761.2664236","DOIUrl":"https://doi.org/10.1145/2663761.2664236","url":null,"abstract":"The scheduling of real-time parallel tasks on multiprocessor systems is more complicated than the one of independent sequential tasks, specially for the Directed Acyclic Graph (DAG) parallel model. The complexity is due to the structure of the DAG tasks and the precedence constraints between their subtasks. The trivial DAG scheduling method is to apply directly common real-time scheduling algorithms despite their lack of compatibility with the parallel model. Another scheduling method called the stretching method is summarized as converting each parallel DAG task in the set into a collection of independent sequential threads that are easier to be scheduled.\u0000 In this paper, we are interested in analyzing global pre-emptive scheduling of DAGs using both methods by showing that both methods are not comparable in the case of using Deadline Monotonic (DM) and Earliest Deadline First (EDF) scheduling algorithms. Then we use extensive simulations to compare and analyze their performance.\u0000 A category with the (minimum) three required fields","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115977619","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}
S. Aminikhanghahi, Sung Y. Shin, Wei Wang, Seong‐Ho Son, S. Jeon
{"title":"An optimized support vector machine classifier to extract abnormal features from breast microwave tomography data","authors":"S. Aminikhanghahi, Sung Y. Shin, Wei Wang, Seong‐Ho Son, S. Jeon","doi":"10.1145/2663761.2664230","DOIUrl":"https://doi.org/10.1145/2663761.2664230","url":null,"abstract":"Microwave Tomography (MT) as a new electronic healthcare system tries to measure dielectric properties of tissues inside the breast and helps early breast cancer detection. In this paper, we propose a new classifier to extract tumor information from Microwave Tomography raw data to determine whether the breast needs further diagnosis or not. The proposed method uses grid search algorithm to optimize support vector machine classifier. The results show that optimized SVM can improve measure of performances such as MCC, specificity and sensitivity. The new classifier can be a promising tool to provide preliminary decision support information to physicians for further diagnosis.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116488791","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":"Evaluating the performance impact of RTR-BIRD in origin validation","authors":"Kyoungha Kim, Ik-hyeon Jang, Yanggon Kim","doi":"10.1145/2663761.2664202","DOIUrl":"https://doi.org/10.1145/2663761.2664202","url":null,"abstract":"RTR-BIRD we previously developed is the only software router that is not only capable of the resource public key infrastructure (RPKI) but able to access the route origin authorizations (ROAs) in the practical validated cache. Although RTR-BIRD practically validates origins as opposed to QuaggaSRx implemented by the national institute of standards and technology (NIST), the routing performance of RTR-BIRD in processing a BGP update message was 4900 times worse than the routing performance of BIRD; BIRD took 0.4 millisecond whereas RTR-BIRD took 1.96 seconds per BGP update message. The difference in performance could be neglected if RTR-BIRD deals with only few routing updates in a highly discrete period. The decrease in performance, however, can be considerable if thousands of routing updates are concurrently received by a RTR-BIRD router---for instance, at router-startup or at router-reboot. Moreover, the performance degradation possibly disconnects BGP-peering sessions or imprecisely validates origins. In order to investigate the degradation in performance of RTR-BIRD, we broke up RTRPKI into components depending on its functionalities because the main difference between RTR-BIRD and BIRD is RTRPKI, which figuratively validates origins. From the separation of RTRPKI, we developed few more variations of RTRPKI by differentiating them in components to validate origins. Our simulation results in comparing RTRPKI with those variations revealed that the most problematic component of RTRPKI was the delay to synchronize RTRPKI to its associated cache server, so we detached the synchronization from the origin validation cycle (OVC) of RTR-BIRD. Consequently, our simulation results on the updated RTR-BIRD showed that the updated version validates origins approximately 4475 times faster than the original RTR-BIRD. Furthermore, the new version showed 100 percent accuracy in validating origins by eliminating at most two percent inconsistency of the validation results presented by the original RTR-BIRD router.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116307251","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":"Post ranking in a blogosphere","authors":"Won-Seok Hwang, Sang-Wook Kim","doi":"10.1145/2663761.2664204","DOIUrl":"https://doi.org/10.1145/2663761.2664204","url":null,"abstract":"The existing post ranking algorithms overlook the category and the time interval, which are valuable information to improve the accuracy of algorithms. The category, created by a blogger, implies the interested topics of her/him, and the time interval between the generation of a post and a blog-action is related to the quality of post. This paper proposes two approaches that exploit the category and the time interval, and we apply our approaches to the existing post ranking algorithms, i.e. PostRank, BAITS, BloggerAVG. We evaluate the accuracy of these algorithms by conducting extensive experiments using real-world blog data, and the results show that our approaches help each algorithm improve the accuracy.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122430332","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}
Xing Chen, Wei Yu, D. Griffith, N. Golmie, Guobin Xu
{"title":"On cascading failures and countermeasures based on energy storage in the smart grid","authors":"Xing Chen, Wei Yu, D. Griffith, N. Golmie, Guobin Xu","doi":"10.1145/2663761.2663770","DOIUrl":"https://doi.org/10.1145/2663761.2663770","url":null,"abstract":"Recently, there have been growing concerns about electric power grid security and resilience. The performance of the power grid may suffer from component failures or targeted attacks. A sophisticated adversary may target critical components in the grid, leading to cascading failures and large blackouts. To this end, this paper begins with identifying the most critical components that lead to cascading failures in the grid and then presents a defensive mechanism using energy storage to defend against cascading failures. Based on the optimal power flow control on the standard IEEE power system test cases, we systematically assess component significance, simulate attacks against power grid components, and evaluate the consequences. We also conduct extensive simulations to investigate the effectiveness of deploying Energy Storage Systems (ESSs), in terms of storage capacity and deployment locations, to mitigate cascading failures. Through extensive simulations, our data shows that integrating energy storage systems into the smart grid can efficiently mitigate cascading failures.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123509687","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":"Adapting byte addressable memory storage to user-level file system services","authors":"S. Oikawa","doi":"10.1145/2663761.2666035","DOIUrl":"https://doi.org/10.1145/2663761.2666035","url":null,"abstract":"Widely available distributed file systems for big data processing are implemented as user-level services since the existing file systems, which are implemented in the operating system kernel, cannot satisfy their requirements. They usually employ file systems in the kernel to persistently save their data in their local systems; thus, the kernel is always interposed for their access the storage devices. Now, next generation non-volatile memory technologies are emerging as byte addressable memory devices that can be used as high performance storage, for which the interposition of the kernel is the source of overhead. This paper proposes the adaption of memory storage to user-level file system services and the convergence of such services and memory storage. User-level file system services are connected to memory storage through the library implementation of a file system, and a library file system can directly interact with memory storage through the memory interface by mapping memory storage onto a user process address space. We implemented a library file system on Linux. The experiment results show that the the implemented library file system outperforms the existing file system in the kernel and performs 1.9x and 6.5x faster for reading and writing, respectively, for typical cases.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114558214","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 online multi-object tracking by detection approach based on particle filtering framework","authors":"Zhenhai Wang, Kicheon Hong","doi":"10.1145/2663761.2664216","DOIUrl":"https://doi.org/10.1145/2663761.2664216","url":null,"abstract":"In this paper, we address the problem of automatically detecting and tracking a variable number of persons in complex scenes using a monocular, potentially moving, uncalibrated camera. We propose a novel approach for multi-object tracking by detection in a particle filtering framework. First, in order to improve detection performance, moving objects are automatically extracted using boosting factor and labeling method. Then, multiple objects are tracked in particle filtering framework by adaptively selecting block template according to human model and adaptively updating template using current detection. Finally, we resolve the data association using Hungarian assignment algorithm and compute the observation likelihood function of each particle filter using the associated detection. We present a new method to deal with the variety of the number of objects at random times. The resulting algorithm robustly tracks a variable number of dynamically moving objects in complex scenes with occlusions. The approach relies only on information from the past and is suitable for online application, and does not require any camera or ground plane calibration. We evaluate the performance on a variety of datasets and show that it improves upon state-of-the-art methods.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121850318","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":"Unsupervised detection of obfuscated diverse attacks in recommender systems","authors":"S. S. Hashmi, Sang-Wook Kim","doi":"10.1145/2663761.2664232","DOIUrl":"https://doi.org/10.1145/2663761.2664232","url":null,"abstract":"Biased ratings of attack profiles have a significant impact on the effectiveness of collaborative recommender systems. Previous work has shown standard memory-based recommendation algorithms, such as k-nearest neighbor (kNN), susceptible to the attacks compared with model-based collaborative filtering (CF) algorithms. An obfuscated diverse attack strategy made model-based algorithms vulnerable to attacks. Attack profiles generated with this strategy are also able to avoid principal component analysis (PCA)-based detection. This paper proposes an algorithm to detect obfuscated diverse attack profiles. Profiles' pairwise covariance with each other is used to separate attack profiles from genuine profiles. Through extensive experiments, we demonstrate that our algorithm detects these attack profiles with high accuracy.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125519485","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":"DroidDolphin: a dynamic Android malware detection framework using big data and machine learning","authors":"Wen-Chieh Wu, Shih-Hao Hung","doi":"10.1145/2663761.2664223","DOIUrl":"https://doi.org/10.1145/2663761.2664223","url":null,"abstract":"Smartphones are getting more and more popular nowadays with various kinds of applications to make our lives more convenient. Unfortunately, malicious applications, also known as malware, arises as well. A user is often tempted into install a malware without any awareness, and the malware steals the users' personal information. Some malware would send SMS or make phone calls, which result in additional charges. Thus, detection of malware is critical to protect smartphone users.\u0000 In this paper, we proposed DroidDolphin, a dynamic malware analysis framework which leverages the technologies of GUI-based testing, big data analysis, and machine learning to detect malicious Android applications. Based on our automatic testing tools, we were able to extract useful static and dynamic features from a training dataset composed with 32,000 benign and 32,000 malicious applications. Our preliminary results showed that the prediction accuracy reaches 86.1% and F-score reaches 0.857. As the dataset increases, the accuracy of detection increases significantly, which makes this methodology promising.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131688143","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":"Meta-routing over heterogeneous networks in M2M systems","authors":"C. Shih, Guan-Fan Wu","doi":"10.1145/2663761.2666033","DOIUrl":"https://doi.org/10.1145/2663761.2666033","url":null,"abstract":"Machine-to-machine (M2M) allows autonomous computation systems to communicate with each other and to collaborately accomplish the works without human intervention. Each node in M2M network may have different communication interface such as Zigbee, Z-wave and Wi-Fi. We design a routing framework that can enable M2M to transmit data across heterogeneous network interfaces via selecting a routing path under given transmission policy. The framework can work in the dynamic network environment, such as including a new node or losting an existin node, the framework will reconstruct the route automatically without developer/administrator instruction at run-time. A new node broadcasts a route exploration message to the network when it joins to the network. Every node updates the routing table to the new node according to the exploration message. Then the new node will send request message to the neighbors to receive the reply messages from them. After collecting the reply messages, the new node can then build the routing table itself. When a node detects a connection failure, it can recover the routing table from nearby neighbors. The experiment results show that we show that the meta-route framework determine throughput policy with high throughput and high energy consumption, and energy policy with low throughput and low energy consumption.","PeriodicalId":120340,"journal":{"name":"Research in Adaptive and Convergent Systems","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129680026","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}