Обнаружение транспортных средств на изображениях загородных шоссе на основе метода Single shot multibox Detector

Nowadays, deep neural networks are widely used in mission critical systems such as healthcare, self-driving vehicles, and military which have direct impact on human lives However, the black-box nature of deep neural networks challenges its use in mission critical applications, raising ethical and judicial concerns inducing lack of trust Explainable Artificial Intelligence (XAI) is a field of Artificial Intelligence (AI) that promotes a set of tools, techniques, and algorithms that can generate high-quality interpretable, intuitive, human-understandable explanations of AI decisions In addition to providing a holistic view of the current XAI landscape in deep learning, this paper provides mathematical summaries of seminal work We start by proposing a taxonomy and categorizing the XAI techniques based on their scope of explanations, methodology behind the algorithms, and explanation level or usage which helps build trustworthy, interpretable, and self-explanatory deep learning models We then describe the main principles used in XAI research and present the historical timeline for landmark studies in XAI from 2007 to 2020 After explaining each category of algorithms and approaches in detail, we then evaluate the explanation maps generated by eight XAI algorithms on image data, discuss the limitations of this approach, and provide potential future directions to improve XAI evaluation

Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey

Recently, renewable energies are widely used instead of the fuel energies due to their individual potentials such as its availability, low price and environmentally friendly. One of the most important renewable energies is wind power. As a result, investment in wind power is one of the most interesting research to maximize the profit of the investment and market clearing. In this paper, bi-level optimization technique is proposed to maximize the investment problem and market clearing for the wind power at the same time and in one single problem. Then, karush–kuhn–tucker (KKT) conditions and mathematical programming with equilibrium constraints (MPEC) are applied and tried to find one level optimization problem. Due to the nonlinearity of the optimization equation, the Fortuny-Amat & McCarl (FM) linearization technique is used to linearize the model. Finally, the proposed technique is applied to the IEEE 24 buses. The result proves that the optimization analysis is very easy, fast and accurate due to the linear characteristic of the system. All the simulation results are carried out in MATLAB and GAMS softwares.

/pdf/an-optimization-technique-based-on-profit-of-investment-and-4ahmj2opms.pdf

An Optimization Technique Based on Profit of Investment and Market Clearing in Wind Power Systems

This paper investigates the impact of uncoordinated, coordinated, and smart charging of plug-in hybrid electric vehicles (PHEVs) on the optimal operation of microgrids (MGs) incorporating the dynamic line rating (DLR) security constraint. The DLR constraint, particularly in the islanding mode, influences the ampacity of MG feeders, when distribution lines reach their maximum capacity. To overcome any line outage or contingency situation, smart PHEVs are utilized to help improve the grid security. However, using PHEVs can cause higher power losses and feeder overloading issues. To address these concerns, a reconfiguration technique is employed in this paper. A heuristic algorithm, known as the collective decision-based optimization algorithm, is utilized to overcome the non-convexity and nonlinearity of the problem. The unscented transform technique is employed to model DLR uncertainties caused by solar radiation, load demand, and weather temperature, as well as PHEVs’ uncertainties caused by varying charging strategies, numbers of PHEVs being charged, charging start time, and charging duration. Moreover, a deep learning gated recurrent unit technique is designed to forecast renewable power output for mitigating the uncertainties in renewable energy components. A modified IEEE 33-bus test network is deployed to evaluate the efficiency and performance of the proposed model.

Stochastic Modeling and Integration of Plug-In Hybrid Electric Vehicles in Reconfigurable Microgrids With Deep Learning-Based Forecasting

Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen the learning capability of such networks from limited samples, still remains a challenge. Techniques like Meta-Learning and/or few-shot learning showed promising results, where they can learn or generalize to a novel category/task based on prior knowledge. In this paper, we perform a study of the existing few-shot meta-learning techniques in the computer vision domain based on their method and evaluation metrics. We provide a taxonomy for the techniques and categorize them as data-augmentation, embedding, optimization and semantics based learning for few-shot, one-shot and zero-shot settings. We then describe the seminal work done in each category and discuss their approach towards solving the predicament of learning from few samples. Lastly we provide a comparison of these techniques on the commonly used benchmark datasets: Omniglot, and MiniImagenet, along with a discussion towards the future direction of improving the performance of these techniques towards the final goal of outperforming humans.

Learning from Few Samples: A Survey.

Object detection is an important area of research in computer vision. One of the challenges in this domain is to detect objects in real time using the minimum resources possible. In this paper, we describe a robust method for real time object detection that can be used on low-profile hardware and needs little training. This approach is based on a discrete adaptive color thresholding method. By applying a redistribution algorithm based on color specifications on the training data, the system would be able to detect colors that may appear with small changes in lighting conditions in the scene. The detection algorithm uses a spatial voting method to improve the accuracy of the result. These characteristics make this method a robust tool in ubiquitous computing and also help intelligent environments to act/react more properly by increasing their awareness of the environment.

Real time object detection using a novel adaptive color thresholding method

Simultaneous multithreading (SMT) provides a method to improve resource uti-lization and performance of superscalar CPUs by sharing key data-path components among multiple independent threads. As threads have unstable behavior, Effective use of critical resources among threads is a challenge to SMT. One of most critical shared resources in the pipeline is Issue Queue (IQ) so putting a limit on its occupation by each thread leads improving in the overall throughput; however, to accommodate the transient behavior of each thread, setting a limit (cap) should be done properly in real time in order to preclude under-utilization (thus, under-achieving) due to over-capping, or starvation for some threads due to under- capping. In this paper, a simple dynamic algorithm is proposed to adjust the cap value for each thread in real time according to the number of memory instructions of each thread. The simulation results show a considerable improvement in IPC over the regular no-capping technique and even a performance superior to the fixed capping approach by using the proposed method.

Improving IPC in simultaneous multi-threading (SMT) processors by capping IQ utilization according to dispatched memory instructions

Effective use of critical resources among threads remains a challenge to Simultaneous multithreading (SMT) due to transient behaviors of threads. As Issue Queue (IQ) is regarded as one of most critical shared resources in the pipeline, putting a limit on its occupation by each thread may easily improve the overall throughput, however, such a limit (cap) should be set properly in real time to accommodate the transient behavior of each thread. We propose a simple dynamic algorithm to adjust the cap value for each thread in real time according to its activeness in terms of its dispatching and issuing activities. The simulation results show that the proposed technique not only achieves a significant improvement in IPC over the regular no-capping technique, but also demonstrates a performance superior to the fixed capping approach.

A Real-Time Per-Thread IQ-Capping Technique for Simultaneous Multi-threading (SMT) Processors

High performance computing (HPC) means the aggregation of computational power to increase the ability of processing large problems in science, engineering, and business. HPC on the cloud allows performing on demand HPC tasks by high performance clusters in a cloud environment. The connection structure of the nodes in HPC clusters should provide fast internode communication. It is important that scalability is preserved as well. This paper proposes a hypercube topology for connecting the nodes in an HPC cluster that facilitates fast communications between nodes. In addition, the proposed hypercube topology provides the ability to scale, which is needed for high performance computing on the cloud.

Hypercube based clusters in Cloud Computing

Image captioning is the process of analyzing an image and generating a textual description according to objects and actions in the image. Thus, both image processing and natural language understanding are required for an image captioning system. Applications of image captioning can vary from assisting visually impaired people to detecting fake news in social media. One of significant utilizations of image captioning would be the detection of particular actions in images. In this paper, we use image captioning to produce a textual description from an image. Then we exploit a natural language processing algorithm to extract main components in the produced description. Finally we generate a general graph according to detected components in descriptions of the image. The generated graph shows objects and pairwise relationship between them along with their attributes. Thus, it can be used to determine if there is any particular relation in a sequence of input images.

Amin Sahba

Papers

Real time object detection using a novel adaptive color thresholding method

Improving IPC in simultaneous multi-threading (SMT) processors by capping IQ utilization according to dispatched memory instructions

A Real-Time Per-Thread IQ-Capping Technique for Simultaneous Multi-threading (SMT) Processors

Hypercube based clusters in Cloud Computing

Image Graph Production by Dense Captioning