In this research Connectionist modeling of decision making has been presented. Important areas for decision making in the brain are thalamus, prefrontal cortex and Amygdala. Connectionist modeling with 3 parts representative for these 3 areas is made based the result of Iowa Gambling Task. In many researches Iowa Gambling Task is used to study emotional decision making. In these kind of decision making the role of Amygdala is so important and we expect that a model with two parts (thalamus and Amygdala) can have the best result in modeling participants decisions without considering any part for cortex process. For this purpose 56 participants composed of 20 men and 36 women wanted to do Iowa Gambling Task. Results show that the Networks related to two parts model predict 62. 57 Percent’ s of participant’ s decisions and the 3parts model has 68. 46 Percent’ s of that. In conclusion it can be said that three parts modeling has been more success than mathematical two parts model in predicting the performance of participants and the difference is significant. In other words cortex role in this kind of decision making is quite important.

One of the most important challenges in automatic speech recognition is in the case of difference between the training and testing data. To decrease this difference, the conventional methods try to enhance the speech or use the statistical model adaptation. Training the model in different situations is another example of these methods. The success rate in these methods compared to those of cognitive and recognition systems of human beings seems too much primary. In this paper, an inspiration from human beings' recognition system helped us in developing and implementing a new Connectionist lexical model. Integration of imputation and classification in a single NN for ASR with missing data was investigated. This can be considered as a variant of multi-task learning because we train the imputation and classification tasks in parallel fashion. Cascading of this model and the acoustic model corrects the sequence of the mined phonemes from the acoustic model to the desirable sequence. This approach was implemented on 400 isolated words of TFARSDAT Database (Actual telephone database). In the best case, the phoneme recognition correction increased in 16.9 percent. Incorporating prior knowledge (high level knowledge) in acoustic-phonetic information (lower level) can improve the recognition. By cascading the lexical model and the acoustic model, the feature parameters were corrected based on the inversion techniques in the neural Networks. Speech enhancement by this method had a remarkable effect in the mismatch between the training and testing data. Efficiency of the lexical model and speech enhancement was observed by improving the phonemes' recognition correction in 18 percent compared to the acoustic model.

We address the throughput maximization problem for downlink transmission in DF-relay-assisted cognitive radio Networks (CRNs) based on simultaneous wireless information and power transfer (SWIPT) capability. In this envisioned network, multiple-input multiple-output (MIMO) relay and secondary user (SU) equipment are designed to handle both radio frequency (RF) signal energy harvesting and SWIPT functional tasks. Additionally, the cognitive base station (CBS) communicates with the SU only via the MIMO relay. Based on the considered network model, several combined constraints of the main problem complicate the solution. Therefore, in this paper, we apply heuristic guidelines within the convex optimization framework to handle this complexity. First, consider the problem of maximizing throughput on both sides of the relay separately. Second, each side progresses to solve the complex problem optimally by adopting strategies for solving sub-problems. Finally, these optimal solutions are synthesized by proposing a heuristic iterative power allocation algorithm that satisfies the combinatorial constraints with short convergence times. The performance of the optimal proposed algorithm (OPA) is evaluated against benchmark algorithms via numerical results on optimality, convergence time, constraints’ compliance, and imperfect channel state information (CSI) on the CBS-PU link.

Different types of contact, including contact between node pairs, any-contact of nodes, and contacts of the entire network, are used to characterize social relations in mobile social Networks. Different modes of routing, from the point of view of message delivery semantics, encompass unicasting, multicasting, any-casting, and broadcasting. Studies have shown that using probability distribution functions of contact data, which is mainly assumed to be homogeneous for nodes, improves the performance of these Networks. However, there exists an important challenge in studies on distributions. A lot of works apply the distribution of one type of contact to other types. Hence in routing applications, it causes to use of the distribution of one type of contact for any mode of routing. This study provides a complete solution to model each type of homogeneous contact data distribution and to use them in different modes of routing. We propose a routing algorithm that uses this new model. Results show that our solution improves the average latency of comparing methods Epidemic, TCCB, and DR about 3.5-times, 30%, and 45%, respectively. It achieves a delivery rate of about 5% and 6%, and average latency about 6% and 8% better than that of DR and TCCB, respectively.

The goal of many tasks in the realm of sequence processing is to map a sequence of input data to a sequence of output labels. Long short-term memory (LSTM), a type of recurrent neural network (RNN), equipped with Connectionist temporal classification (CTC) has been proved to be one of the most suitable tools for such tasks. With the aid of CTC, the existence of per-frame labeled sequences are no longer necessary and it suffices to only knowing the sequence of labels. However, in CTC, only a single state is assigned to each label and consequently, LSTM would not learn the intra-label relationships. In this paper, we propose to remedy this weakness by increasing the number of states assigned to each label and actively modeling such intra-label transitions. On the other hand, the output of a CTC network usually corresponds to the set of all possible labels along with a blank. One of the uses of blank is in the recognition of multiple consecutive identical labels. Assigning more than one state to each label, we can also decode consecutive identical labels without resorting to the blank. We investigated the effect of increasing the number of sub-labels with/without blank on the recognition rate of the system. We performed experiments on two printed and handwritten Arabic datasets. Our experiments showed that while on simple tasks a model without blank may converge faster, on real-world complex datasets use of blank significantly improves the results.