2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2019
This paper presents a new distributed approach for generating all prime numbers in a given interv... more This paper presents a new distributed approach for generating all prime numbers in a given interval of integers. From Eratosthenes, who elaborated the first prime sieve (more than 2000 years ago), to the current generation of parallel computers, which have permitted to reach larger bounds on the interval or to obtain previous results in a shorter time, prime numbers generation still represents an attractive domain of research and plays a central role in cryptography. We propose a fully distributed algorithm for finding all primes in the interval [2; n], based on the wheel sieve and the SMER (Scheduling by Multiple Edge Reversal) multigraph dynamics which runs in O(√(n)) computational complexity, close to the theoretical lower bound on sieve methods, that is O(n), without making use of preprocessing techniques.
Scheduling by Edge Reversal provides an order of operation for nodes in a graph, but maximizing o... more Scheduling by Edge Reversal provides an order of operation for nodes in a graph, but maximizing or minimizing the resulting concurrency is hard. In this paper, we discuss a series of real‐world applications for this technique and propose algorithms for both problems. For maximum concurrency, we prove its general inapproximability and introduce approximation algorithms for classes of graphs. For minimum concurrency, we use hardness and inapproximability results to establish its relation to longest cycles, while also introducing a novel application for assembling musical phrases.
2018 7th Brazilian Conference on Intelligent Systems (BRACIS), 2018
Recommender systems generally are made to predict user preferences' for items. However, in hi... more Recommender systems generally are made to predict user preferences' for items. However, in high dimensional datasets this task demands high computational costs. Taking into account that data distribution changes through time, it is important that online recommender systems have a fast retraining process in order to keep the model updated, delivering accurate predictions. Therefore, we propose a new approach for recommender systems using a weightless neural network, denominated WiSARD. We show that our proposal increases training and prediction processing speed, without decreasing the quality of predictions. First results show that our proposal is 306% faster than the improved regularized singular value decomposition (IRSVD), a well-known state-of-the-art algorithm. Moreover, our proposal still had an improvement of 3.7% regarding the mean absolute error (MAE). We show how to apply the WiSARD algorithm for online recommender systems, its drawbacks, and insights for further research.
2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), 2016
In this study, we propose a variation of the RAdNet for vehicular environments (RAdNet-VE). The p... more In this study, we propose a variation of the RAdNet for vehicular environments (RAdNet-VE). The proposed scheme extends the message header, mechanism for registering interest, and message forwarding mechanism of RAdNet. Based on results obtained from simulation experiments, we compare the performance of RAdNet-VE against that of RAdNet, a basic content-centric network (CCN) using reactive data routing, (CCNr), and a basic CCN using proactive data routing, CCNP. These CCNs provide non-cacheable data services. Moreover, the communication radio standards adopted in the scenarios 1 and 2 were respectively IEEE 802.11n and IEEE 802.11p. The results shown that the performance of the RAdNet-VE was superior to than those of RAdNet, CCNR and CCNP. In this sense, RAdNet-VE protocol (RVEP) presented low communication latencies among nodes of just 20.4ms (scenario 1) and 2.87 ms (scenario 2). Our protocol also presented high data delivery rates, i.e, 83.05% (scenario 1) and 88.05% (scenario 2). Based on these and other results presented in this study, we argue that RAdNet-VE is a feasible alternative to CCNs as information-centric network (ICN) model for VANET, because the RVEP satisfies all of the necessary communication requirements.
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
This work introduces a new methodology for the early detection of epileptic seizure based on the ... more This work introduces a new methodology for the early detection of epileptic seizure based on the WiSARD weightless neural network model and a new approach in terms of preprocessing the electroencephalogram (EEG) data. WiSARD has, among other advantages, the capacity of perform the training phase in a very fast way. This speed in training is due to the fact that WiSARD's neurons work like Random Access Memories (RAM) addressed by input patterns. Promising results were obtained in the anticipation of seizure onsets in four representative patients from the European Database on Epilepsy (EPILEPSIAE). The proposed seizure early detection WNN architecture was explored by varying the detection anticipation (δ) in the 2 to 30 seconds interval, and by adopting 2 and 3 seconds as the width of the Sliding Observation Window (SOW) input. While in the most challenging patient (A) one obtained accuracies from 99.57% (δ=2s; SOW=3s) to 72.56% (δ=30s; SOW=2s), patient D seizures could be detected in the 99.77% (δ=2s; SOW=2s) to 99.93% (δ=30s; SOW=3s) accuracy interval.
Dynamic Trace Memoization (DTM) is a reuse technique that employs memoization tables to skip the ... more Dynamic Trace Memoization (DTM) is a reuse technique that employs memoization tables to skip the execution of sequences of redundant instructions. DTM thus extends the concept of instruction reuse to larger grained units and, contrary to other proposed reuse schemes, it is not constrained by architectural parameters nor code-level boundaries. For the benchmark programs in the SPECInt95 suite, evaluation results show that DTM improves performance by 5% to 21% with an average of 9.3%. For the largest common subset of the SPECInt95 benchmarks tested in two other previously proposed reuse mechanisms, DTM attains twice the average performance increase for configurations with similar storage capacities. 1 Introduction Experimental studies [1, 2] demonstrate that redundant instructions represent a significant portion of the instructions executed by a program. Redundant instructions are dynamic instances of the same static instructions which execute with the same operand values and therefor...
Proceedings. XI Brazilian Symposium on Integrated Circuit Design (Cat. No.98EX216)
... [3] L. Louca, TA Cook e WH Johnson, “Implementation of IEEE single precision floating point a... more ... [3] L. Louca, TA Cook e WH Johnson, “Implementation of IEEE single precision floating point addition and multiplication on FPGAs”, IEEE FCCM'96, 107-117. [4] L. Maltar CB, FMG França, VC Alves, CL Amorim, technical report, in preparation. ...
2006 Ph.D. Research in Microelectronics and Electronics
In this work an automated conversion method of synchronous circuits into asynchronous ones is pre... more In this work an automated conversion method of synchronous circuits into asynchronous ones is presented. The technique utilizes the synchronous circuit fully synthesized netlist, and employs ASERT - asynchronous scheduling by edge reversal timing - for signaling and synchronization between asynchronous functional units, which are extracted from the functional blocks hierarchical organization conceived by the original synchronous circuit designer. The
The reconstruction of tracks left by particles in a scintillating fiber detector from a high ener... more The reconstruction of tracks left by particles in a scintillating fiber detector from a high energy experiment is discussed. The track reconstruction algorithm is based on the Hough transform and achieves an efficiency above 86%. The algorithm is implemented in a 16-...
It is nowadays common to find users that have to use different machines at work, home, and travel... more It is nowadays common to find users that have to use different machines at work, home, and travel. Such users often spend significant amounts of time sychronising and restarting their work environments. Often, they eventually have to cope with inconsistent data at different locations. ZOS (Zombie Operating System) proposes that users should have a main execution context (or anima) containing not only the user's data, but also application images. Ideally, the anima should reside in a small server, themaster. In ZOS, masters take over other machines, the zombies, and then take advantage of their resources, such as better CPU, better interfaces, more disk, or extra connectivity. We describe our first implementation of ZOS, which, we believe, demonstrates that the idea is practical and worthwhile.
2019 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), 2019
This paper presents a new distributed approach for generating all prime numbers in a given interv... more This paper presents a new distributed approach for generating all prime numbers in a given interval of integers. From Eratosthenes, who elaborated the first prime sieve (more than 2000 years ago), to the current generation of parallel computers, which have permitted to reach larger bounds on the interval or to obtain previous results in a shorter time, prime numbers generation still represents an attractive domain of research and plays a central role in cryptography. We propose a fully distributed algorithm for finding all primes in the interval [2; n], based on the wheel sieve and the SMER (Scheduling by Multiple Edge Reversal) multigraph dynamics which runs in O(√(n)) computational complexity, close to the theoretical lower bound on sieve methods, that is O(n), without making use of preprocessing techniques.
Scheduling by Edge Reversal provides an order of operation for nodes in a graph, but maximizing o... more Scheduling by Edge Reversal provides an order of operation for nodes in a graph, but maximizing or minimizing the resulting concurrency is hard. In this paper, we discuss a series of real‐world applications for this technique and propose algorithms for both problems. For maximum concurrency, we prove its general inapproximability and introduce approximation algorithms for classes of graphs. For minimum concurrency, we use hardness and inapproximability results to establish its relation to longest cycles, while also introducing a novel application for assembling musical phrases.
2018 7th Brazilian Conference on Intelligent Systems (BRACIS), 2018
Recommender systems generally are made to predict user preferences' for items. However, in hi... more Recommender systems generally are made to predict user preferences' for items. However, in high dimensional datasets this task demands high computational costs. Taking into account that data distribution changes through time, it is important that online recommender systems have a fast retraining process in order to keep the model updated, delivering accurate predictions. Therefore, we propose a new approach for recommender systems using a weightless neural network, denominated WiSARD. We show that our proposal increases training and prediction processing speed, without decreasing the quality of predictions. First results show that our proposal is 306% faster than the improved regularized singular value decomposition (IRSVD), a well-known state-of-the-art algorithm. Moreover, our proposal still had an improvement of 3.7% regarding the mean absolute error (MAE). We show how to apply the WiSARD algorithm for online recommender systems, its drawbacks, and insights for further research.
2016 IEEE 12th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), 2016
In this study, we propose a variation of the RAdNet for vehicular environments (RAdNet-VE). The p... more In this study, we propose a variation of the RAdNet for vehicular environments (RAdNet-VE). The proposed scheme extends the message header, mechanism for registering interest, and message forwarding mechanism of RAdNet. Based on results obtained from simulation experiments, we compare the performance of RAdNet-VE against that of RAdNet, a basic content-centric network (CCN) using reactive data routing, (CCNr), and a basic CCN using proactive data routing, CCNP. These CCNs provide non-cacheable data services. Moreover, the communication radio standards adopted in the scenarios 1 and 2 were respectively IEEE 802.11n and IEEE 802.11p. The results shown that the performance of the RAdNet-VE was superior to than those of RAdNet, CCNR and CCNP. In this sense, RAdNet-VE protocol (RVEP) presented low communication latencies among nodes of just 20.4ms (scenario 1) and 2.87 ms (scenario 2). Our protocol also presented high data delivery rates, i.e, 83.05% (scenario 1) and 88.05% (scenario 2). Based on these and other results presented in this study, we argue that RAdNet-VE is a feasible alternative to CCNs as information-centric network (ICN) model for VANET, because the RVEP satisfies all of the necessary communication requirements.
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
This work introduces a new methodology for the early detection of epileptic seizure based on the ... more This work introduces a new methodology for the early detection of epileptic seizure based on the WiSARD weightless neural network model and a new approach in terms of preprocessing the electroencephalogram (EEG) data. WiSARD has, among other advantages, the capacity of perform the training phase in a very fast way. This speed in training is due to the fact that WiSARD's neurons work like Random Access Memories (RAM) addressed by input patterns. Promising results were obtained in the anticipation of seizure onsets in four representative patients from the European Database on Epilepsy (EPILEPSIAE). The proposed seizure early detection WNN architecture was explored by varying the detection anticipation (δ) in the 2 to 30 seconds interval, and by adopting 2 and 3 seconds as the width of the Sliding Observation Window (SOW) input. While in the most challenging patient (A) one obtained accuracies from 99.57% (δ=2s; SOW=3s) to 72.56% (δ=30s; SOW=2s), patient D seizures could be detected in the 99.77% (δ=2s; SOW=2s) to 99.93% (δ=30s; SOW=3s) accuracy interval.
Dynamic Trace Memoization (DTM) is a reuse technique that employs memoization tables to skip the ... more Dynamic Trace Memoization (DTM) is a reuse technique that employs memoization tables to skip the execution of sequences of redundant instructions. DTM thus extends the concept of instruction reuse to larger grained units and, contrary to other proposed reuse schemes, it is not constrained by architectural parameters nor code-level boundaries. For the benchmark programs in the SPECInt95 suite, evaluation results show that DTM improves performance by 5% to 21% with an average of 9.3%. For the largest common subset of the SPECInt95 benchmarks tested in two other previously proposed reuse mechanisms, DTM attains twice the average performance increase for configurations with similar storage capacities. 1 Introduction Experimental studies [1, 2] demonstrate that redundant instructions represent a significant portion of the instructions executed by a program. Redundant instructions are dynamic instances of the same static instructions which execute with the same operand values and therefor...
Proceedings. XI Brazilian Symposium on Integrated Circuit Design (Cat. No.98EX216)
... [3] L. Louca, TA Cook e WH Johnson, “Implementation of IEEE single precision floating point a... more ... [3] L. Louca, TA Cook e WH Johnson, “Implementation of IEEE single precision floating point addition and multiplication on FPGAs”, IEEE FCCM'96, 107-117. [4] L. Maltar CB, FMG França, VC Alves, CL Amorim, technical report, in preparation. ...
2006 Ph.D. Research in Microelectronics and Electronics
In this work an automated conversion method of synchronous circuits into asynchronous ones is pre... more In this work an automated conversion method of synchronous circuits into asynchronous ones is presented. The technique utilizes the synchronous circuit fully synthesized netlist, and employs ASERT - asynchronous scheduling by edge reversal timing - for signaling and synchronization between asynchronous functional units, which are extracted from the functional blocks hierarchical organization conceived by the original synchronous circuit designer. The
The reconstruction of tracks left by particles in a scintillating fiber detector from a high ener... more The reconstruction of tracks left by particles in a scintillating fiber detector from a high energy experiment is discussed. The track reconstruction algorithm is based on the Hough transform and achieves an efficiency above 86%. The algorithm is implemented in a 16-...
It is nowadays common to find users that have to use different machines at work, home, and travel... more It is nowadays common to find users that have to use different machines at work, home, and travel. Such users often spend significant amounts of time sychronising and restarting their work environments. Often, they eventually have to cope with inconsistent data at different locations. ZOS (Zombie Operating System) proposes that users should have a main execution context (or anima) containing not only the user's data, but also application images. Ideally, the anima should reside in a small server, themaster. In ZOS, masters take over other machines, the zombies, and then take advantage of their resources, such as better CPU, better interfaces, more disk, or extra connectivity. We describe our first implementation of ZOS, which, we believe, demonstrates that the idea is practical and worthwhile.
Uploads
Papers by Felipe M.G. França