| 1. |
- Najib, Muhammad Sharfi, et al.
(författare)
-
Agarwood classification: A Case-Based Reasoning approach based on E-nose
- 2012
-
Ingår i: Proceedings - 2012 IEEE 8th International Colloquium on Signal Processing and Its Applications, CSPA 2012. - 9781467309615 ; , s. 120-126
-
Konferensbidrag (refereegranskat)abstract
- Using an array of sensors (E-nose) to classify Agarwood has proven to be successful and produced performance close to an expert level (90% of expert level performance) but it has proven difficult to eliminate misclassifications without over-fitting. In our effort to improve our result we explored a self-improving Case-Based Reasoning approach and reached 100% correct classification. Case-Based Reasoning is an approach that will learn from every new classified case and hence the risk for misclassification is reduced. Also when new cases have to be classified that have never occurred before the system will avoid misclassification (similarity measurement is low). The approach also enables indeterminism; in reality a sample may be both close to a good case and a bad case and need further exploration by experts. The approach also handles natural variants in the wood samples well; both low-quality and high-quality samples may spread considerably in the context of E-nose readings and there is no model available of low or high quality.
|
|
| 2. |
- Saeedpoor, M., et al.
(författare)
-
A servqual model approach integrated with fuzzy AHP and fuzzy topsis methodologies to rank life insurance firms
- 2015
-
Ingår i: International Annual Conference of the American Society for Engineering Management 2015, ASEM 2015. - 9781510816022 ; , s. 605-614
-
Konferensbidrag (refereegranskat)abstract
- Ranking life insurance firms, particularly regarding customer-oriented criteria, has become a significant research priority of many insurance research centers. This is mainly due to the effective role of life insurance in improving the capital market and the role of service quality in customer satisfaction. This issue has remained one of the major topics associated with insurance industry which has not been sufficiently explored in the literature. This study aims at prioritizing insurance firms which hold the majority proportion of Iran's total life insurance market. Life insurers are assessed and ranked with regard to 5 criteria of customer service quality in the SERVQUAL model as well as opinions of 43 qualified insurance brokers in Tehran, Iran. Fuzzy Analytic Hierarchy Process (FAHP) is utilized to determine the importance weight of each criterion of the SERVQUAL (service quality) model. After which, the Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (Fuzzy TOPSIS) is applied in order to rank the firms. Both Multiple Attribute Decision Making (MADM) methods are conducted in the fuzzy environment to handle the uncertainty and impreciseness of one's subjective judgments. The results revealed the ranking of 13 Iranian insurance companies in the context of life insurance.
|
|
| 3. |
- Bidgoli, Ali M., et al.
(författare)
-
NeuroPIM : Felxible Neural Accelerator for Processing-in-Memory Architectures
- 2023
-
Ingår i: Proceedings - 2023 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems, DDECS 2023. - : Institute of Electrical and Electronics Engineers Inc.. - 9798350332773 ; , s. 51-56
-
Konferensbidrag (refereegranskat)abstract
- The performance of microprocessors under many modern workloads is mainly limited by the off-chip memory bandwidth. The emerging process-in-memory paradigm present a unique opportunity to reduce data movement overheads by moving computation closer to memory. State-of-the-art processing-in-memory proposals stack a logic layer on top of one or multiple memory layers in a 3D fashion and leverage the logic layer to build near-memory processing units. Such processing units are either application-specific accelerators or general-purpose cores. In this paper, we present NeuroPIM, a new processing-in-memory architecture that uses a neural network as the memory-side general-purpose accelerator. This design is mainly motivated by the observation that in many real-world applications, some program regions, or even the entire program, can be replaced by a neural network that is learned to approximate the program's output. NeuroPIM benefits from both the flexibility of general-purpose processors and superior performance of application-specific accelerators. Experimental results show that NeuroPIM provides up to 41% speedup over a processor-side neural network accelerator and up to 8x speedup over a general-purpose processor.
|
|
| 4. |
- Dehnavi, S., et al.
(författare)
-
Towards an actor-based approach to design verified ROS-based robotic programs using rebeca
- 2019
-
Ingår i: Procedia Computer Science. - : Elsevier B.V.. - 1877-0509. ; , s. 59-68
-
Konferensbidrag (refereegranskat)abstract
- Robotic technology helps humans in different areas such as manufacturing, health care and education. Due to the ubiquitous revolution, today's focus is on mobile robots and their applications in a variety of cyber-physical systems. ROS is a wll-known and powerful middleware that facilitates software development for mobile robots. However, this middleware does not support assuring properties such as timeliness and safety of ROS-based software. In this paper we present an integration of Timed Rebeca modeling language with ROS to synthesize verified robotic software. First, a conceptual model of robotic programs is developed using Timed Rebeca. After verifying a set of user-defined correctness properties on this model, it is translated to a ROS program automatically. Experiments on some small-scale case studies illustrates the applicability of the proposed integration method.
|
|
| 5. |
- Eziama, E., et al.
(författare)
-
Machine learning-based recommendation trust model for machine-to-machine communication
- 2018
-
Ingår i: 2018 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT 2018. - : Institute of Electrical and Electronics Engineers Inc.. - 9781538675687
-
Konferensbidrag (refereegranskat)abstract
- The Machine Type Communication Devices (MTCDs) are usually based on Internet Protocol (IP), which can cause billions of connected objects to be part of the Internet. The enormous amount of data coming from these devices are quite heterogeneous in nature, which can lead to security issues, such as injection attacks, ballot stuffing, and bad mouthing. Consequently, this work considers machine learning trust evaluation as an effective and accurate option for solving the issues associate with security threats. In this paper, a comparative analysis is carried out with five different machine learning approaches: Naive Bayes (NB), Decision Tree (DT), Linear and Radial Support Vector Machine (SVM), KNearest Neighbor (KNN), and Random Forest (RF). As a critical element of the research, the recommendations consider different Machine-to-Machine (M2M) communication nodes with regard to their ability to identify malicious and honest information. To validate the performances of these models, two trust computation measures were used: Receiver Operating Characteristics (ROCs), Precision and Recall. The malicious data was formulated in Matlab. A scenario was created where 50% of the information were modified to be malicious. The malicious nodes were varied in the ranges of 10%, 20%, 30%, 40%, and the results were carefully analyzed.
|
|
| 6. |
- Eziama, Elvin, et al.
(författare)
-
Malicious Node Detection in Vehicular Ad-Hoc Network Using Machine Learning and Deep Learning
- 2018
-
Ingår i: 2018 IEEE GLOBECOM WORKSHOPS (GC WKSHPS). - : IEEE. - 9781538649206
-
Konferensbidrag (refereegranskat)abstract
- Vehicular Ad hoc Networks (VANETs) provide effective vehicular operation for safety as well as greener and more efficient communication of vehicles in the Dedicated Short Range Communication (DRSC). The dynamic nature of the vehicular network topology has posed many security challenges for effective communication among vehicles. Consequently, models have been applied in the literature to checkmate the security issues in the vehicular networks. Existing models lack flexibility and sufficient functionality in capturing the dynamic behaviors of malicious nodes in the highly volatile vehicular communication systems. Given that existing models have failed to meet up with the challenges involved in vehicular network topology, it has become imperative to adopt complementary measures to tackle the security issues in the system. The approach of trust model with respect to Machine/Deep Learning (ML/DL) is proposed in the paper due to the gap in the area of network security by the existing models. The proposed model is to provide a data-driven approach in solving the security challenges in dynamic networks. This model goes beyond the existing works conceptually by modeling trust as a classification process and the extraction of relevant features using a hybrid model like Bayesian Neural Network that combines deep learning with probabilistic modeling for intelligent decision and effective generalization in trust computation of honest and dishonest nodes in the network.
|
|
| 7. |
- Loni, Mohammad, et al.
(författare)
-
NeuroPower : Designing Energy Efficient Convolutional Neural Network Architecture for Embedded Systems
- 2019
-
Ingår i: Lecture Notes in Computer Science, Volume 11727. - Munich, Germany : Springer. - 9783030304867 ; 11727 LNCS, s. 208-222
-
Konferensbidrag (refereegranskat)abstract
- Convolutional Neural Networks (CNNs) suffer from energy-hungry implementation due to their computation and memory intensive processing patterns. This problem is even more significant by the proliferation of CNNs on embedded platforms. To overcome this problem, we offer NeuroPower as an automatic framework that designs a highly optimized and energy efficient set of CNN architectures for embedded systems. NeuroPower explores and prunes the design space to find improved set of neural architectures. Toward this aim, a multi-objective optimization strategy is integrated to solve Neural Architecture Search (NAS) problem by near-optimal tuning network hyperparameters. The main objectives of the optimization algorithm are network accuracy and number of parameters in the network. The evaluation results show the effectiveness of NeuroPower on energy consumption, compacting rate and inference time compared to other cutting-edge approaches. In comparison with the best results on CIFAR-10/CIFAR-100 datasets, a generated network by NeuroPower presents up to 2.1x/1.56x compression rate, 1.59x/3.46x speedup and 1.52x/1.82x power saving while loses 2.4%/-0.6% accuracy, respectively.
|
|
| 8. |
- Nikoui, T. S., et al.
(författare)
-
Presenting an Edge-based Air Quality Management System for Smart City Scenarios
- 2023
-
Ingår i: Int. Conf. Inf. Knowl. Technol., IKT. - : Institute of Electrical and Electronics Engineers Inc.. - 9798350349412 ; , s. 235-240
-
Konferensbidrag (refereegranskat)abstract
- The IoT as a fast-growing topic attracts attention from the research communities and business owners since the IoT paradigm can improve the ease of life and present new opportunities. The smart city scenario offers technology-based facilities for citizens to enhance their quality of life, public safety, and disaster management. Smart city context includes multiple subsystems with massive numbers and different types of IoT devices. This study focuses on implementing an edge-based air quality management system and presents the requirement analysis phase as the first step to outline the essential requirements. Considering this phase, the presented architecture is defined to improve availability, scalability, and interoperability. Moreover, it provides data analysis and alerting functionalities. The system is implemented using open-source technologies to decrease the cost of development and improve time to market. In addition, several REST APIs are provided to achieve higher interoperability and more efficient integration. The system is evaluated using a real data set, and the presented results indicate that using this model can improve time efficiency while meeting non-functional requirements.
|
|
| 9. |
- Rafiee, Ali, et al.
(författare)
-
Fire and smoke detection using wavelet analysis and disorder characteristics
- 2011
-
Ingår i: ICCRD2011 - 2011 3rd International Conference on Computer Research and Development, vol 3, 2011. - 9781612848396 ; , s. 262-265
-
Konferensbidrag (refereegranskat)abstract
- Fire and smoke monitoring systems are useful in different industry such as military, social security and economical. The recent methods for fire and smoke detection are used only motion and color characteristics thus many wrong alarms are happening and this is decrease the performance of the systems. This research presents a new method for fire and smoke detection through image processing. In this algorithm all objects in an image is considered and then check them to figure out which objects are smoke and fire. The color, motion and disorder are useful characteristics in fire and smoke detection algorithm. Smoke of fire will blur the whole or part of the images. Thus by processing of the video frames, different objects will detect. Due to evaluate the features of objects, the goal objects (fire and smoke) can be defined easily. Two-dimensional wavelet analysis is used in the presented method. The results of this research present the proposed features that can reduce the wrong alarms and increase the system performances.
|
|
| 10. |
- Vafadarnikjoo, A., et al.
(författare)
-
A hybrid approach of intuitionistic fuzzy set theory and dematel method to prioritize selection Criteria of bank branches locations
- 2015
-
Ingår i: International Annual Conference of the American Society for Engineering Management 2015, ASEM 2015. - 9781510816022 ; , s. 595-604
-
Konferensbidrag (refereegranskat)abstract
- Optimally locating new bank branches is a strategic decision in banking industry in order to stay competitive. The importance of this issue is primarily due to the fact that locating branches in appropriate sites is one of the main factors in absorbing and satisfying bank customers. This results in a core benefit for banks, particularly in a vibrant competition. In addition, without a set of well-chosen selection criteria and their prominence, the goal of locating suitable sites for bank branches would not be efficiently achieved. In this research, six most widely used criteria for bank branch location consideration are obtained from the literature review. These criteria include demographic attributes, access to public facilities, transportation, competition, cost and flexibility. In order to prioritize these criteria, an integrated methodology of the intuitionistic fuzzy set theory as well as Decision Making Trial and Evaluation Laboratory Model (DEMATEL) technique (i.e. IFDEMATEL) are utilized. The DEMATEL technique considers interrelationships between criteria. Furthermore, the intuitionistic fuzzy set theory, which has some advantages over fuzzy set theory, to include the vagueness and imprecision of subjective judgments of specialists is applied. As a case study, a well-known Iranian public bank in the city of Rasht, Iran is considered. Consequently, the obtained ranks from the integrated method provide useful information for bank managers in determining efficient locations of their new branches.
|
|
