Comparing ANN to HMM in implementing limited Arabic vocabulary ASR systems

In this paper we investigated Artificial Neural Networks (ANN) based Automatic Speech Recognition (ASR) by using limited Arabic vocabulary corpora. These limited Arabic vocabulary subsets are digits and vowels carried by specific carrier words. In addition to this, Hidden Markov Model (HMM) based ASR systems are designed and compared to two ANN based systems, namely Multilayer Perceptron (MLP) and recurrent architectures, by using the same corpora. All systems are isolated word speech recognizers. The ANN based recognition system achieved 99.5% correct digit recognition. On the other hand, the HMM based recognition system achieved 98.1% correct digit recognition. With vowels carrier words, the MLP and recurrent ANN based recognition systems achieved 92.13% and 98.06, respectively, correct vowel recognition; but the HMM based recognition system achieved 91.6% correct vowel recognition.     

Fixed‐Time Synchronization of a Class of Second‐Order Nonlinear Leader‐Following Multi‐Agent Systems

The fixed‐time synchronization problem for a class of second‐order nonlinear multi‐agent systems with a leader‐follower architecture is investigated in this paper. To achieve the fixed‐time tracking task, the design procedure is divided into two steps. At the first step, a distributed fixed‐time observer is designed for each agent to estimate the leader's state in a fixed time. Then, at the second step, based on the technique of adding a power integrator, a fixed‐time tracking controller for each agent is proposed such that the estimate leader's state can be tracked in a fixed time. Finally, an observer‐based fixed‐time controller is developed such that the leader can be tracked by all the followers in a fixed time, which can be predetermined. Simulations are presented to verify the effectiveness of the proposed approach.     

Automated Machine Learning Enabled Cybersecurity Threat Detection in Internet of Things Environment

Recently, Internet of Things (IoT) devices produces massive quantity of data from distinct sources that get transmitted over public networks. Cybersecurity becomes a challenging issue in the IoT environment where the existence of cyber threats needs to be resolved. The development of automated tools for cyber threat detection and classification using machine learning (ML) and artificial intelligence (AI) tools become essential to accomplish security in the IoT environment. It is needed to minimize security issues related to IoT gadgets effectively. Therefore, this article introduces a new Mayfly optimization (MFO) with regularized extreme learning machine (RELM) model, named MFO-RELM for Cybersecurity Threat Detection and classification in IoT environment. The presented MFO-RELM technique accomplishes the effectual identification of cybersecurity threats that exist in the IoT environment. For accomplishing this, the MFO-RELM model pre-processes the actual IoT data into a meaningful format. In addition, the RELM model receives the pre-processed data and carries out the classification process. In order to boost the performance of the RELM model, the MFO algorithm has been employed to it. The performance validation of the MFO-RELM model is tested using standard datasets and the results highlighted the better outcomes of the MFO-RELM model under distinct aspects.     

Assembling components with behavioural contracts

Component based design is a new paradigm to build distributed systems and applications. The problem of compositional verification of such systems is however still open. We investigate methods and concepts for the provision of “sound” assemblies. We define a behavioural interface type language endowed with a (decidable) set of interface compatibilty and subtyping rules. We define an abstract, dynamic, multi-threaded, component model, encompassing both client/server and peer to peer communication patterns. Based on the notion of compliance of components to their interfaces, we define the concepts of “contract” and “contract satisfaction”. This leads to sound assemblies of components, which possess interesting properties, such as “external deadlockfreeness” and “message consumption”.     

Power estimation for large sequential circuits

A power estimation approach is presented in which blocks of consecutive vectors are selected at random from a user-supplied realistic input vector set and the circuit is simulated for each block starting from an unknown state. This leads to two (upper and lower) bounds on the desired power value which can be quite tight (under 10% difference between the two in many cases). As a result, the power dissipation is obtained by simulating only a fraction of the potentially very large vector set     

Compressive strength and stability of sustainable self-consolidating concrete containing fly ash,silica fume,and GGBS

This paper presents the findings of an experimental program seeking to understand the effect of mineral admixtures on fresh and hardened properties of sustainable self-consolidating concrete (SCC) mixes where up to 80% of Portland cement was replaced with fly ash, silica fume, or ground granulated blast furnace slag. Compressive strength of SCC mixes was measured after 3, 7, and 28 days of moist curing. It was concluded in this study that increasing the dosage of fly ash increases concrete flow but also decreases segregation resistance. In addition, for the water-to-cement ratio of 0.36 used in this study, it was observed that the compressive strength decreases compared to control mix after 28 days of curing when cement was partially replaced by 10%, 30%, and 40%of fly ash. However, a fly ash replacement ratio of 20% increased the compressive strength by a small margin compared to the control mix. Replacing cement with silica fume at 5%, 10%, 15%, and 20% was found to increase compressive strength of SCC mixes compared to the control mix. However, the highest 28 day compressive strength of 95.3 MPa occurred with SCC mixes in which 15% of the cement was replaced with silica fume.