Cognitive Computation and Systems最新文献

The online recommendation system has benefited the traditional restaurant business economically. However, finding the best restaurant during rush time and visiting new places is tough. This objective is addressed through a restaurant recommendation approach, which impacts the human decision-making method. With the help of collaborative filtering, some user-based recommendation systems were designed to generate the best recommendation based on user choices. Thus, a user preferences-based method is presented using A Lite Bidirectional Encoder Representations from Transformers and Simple Recurrent Unit to suggest restaurants based on user preferences. Here, a publicly available dataset from Kaggle called Kzomato is used with 9552 samples and 21 features. And the system obtained an F1-score, precision, and recall of 86%, which will save time and provide the best recommendation based on user preferences easily.

An improved method for recognising clouds on the ground map is proposed incorporating the DeepLabV3+ model to solve three issues. Firstly, an image preprocessing module is developed to enrich image quality, particularly at night, as clouds can appear to be too blurry to distinguish. Secondly, the CBAM attention mechanism is applied to safeguard texture and boundary information, ensuring the depiction of cirrus edges is not lost. Finally, the feature extraction network can be optimised to enhance the model and decrease its computational complexity. In comparison to the original model, the accuracy of the proposed method increased by 10.89%, resulting in an overall accuracy of 94.18%. Furthermore, the MIoU has improved from 66.02% to 79.31%. The number of parameters was reduced by 51.45% to 13.4 M. Of the various cloud types, the improvement in cirrus is particularly striking, with the MIoU increasing from 1.78% to 56.01%.

IT services can be requested via cloud computing, a model based on services as well as the Internet. It includes all computer systems resources from hardware components to software platforms and software applications in a distributed environment. Scheduling is a key step in processing tasks using remote resources. Serious issues have been brought forward, including the ineffective use of resources and task execution failure. The concurrent provision of fault tolerance and resource optimisation is achallenging task. In the context of cloud computing, this research offers a brand-new job scheduling and fault-tolerant system. Tasks submitted by users are taken as an input for the proposed method. Several virtual machines (VM) are initially arranged for scheduling work and execution process. Initially, Horse Herd Optimisation is employed here to allocate the job based on key factors such as deadline and user budget. Once the jobs are assigned to each VM, then each job's deadline is confirmed and transferred to VM which has sufficient capacity. Here, the Reptile Search Optimisation technique is applied to identify the VM error. Any VM that does not have enough capacity is the one that has a problem. When a fault is found, a fault-tolerant process is instantly started. A replication-based fault-tolerant mechanism is used in this manuscript. The proposed approach is tested with several metrics which attains better performance like 80 s response time, turnaround time of 32 s, 17% resource utilisation and a success rate of 92%. Thus the designed model is the best choice for fault-tolerant aware task scheduling.

Due to the improvement in power demand usage, the system causes more stress. Suitable placement of FACTS is introduced to improve power flows, stability, and power system security. An advanced optimal method has been introduced to resolve optimal power flow under various conditions. Five varied FACTS devices were positioned inside the power system to improve system safety at the least cost. Selecting the suitable location and size of FACTS device enabling high security and less cost was proposed using RSA. The objective functions were mitigated based on the RSA's inspiration to improve system security. The placement of the FACTS compensator was based on objective functions like LOSI, voltage deviation, real power loss, investment cost, sensitivity index, fuel costs, and constraints. The proposed model was validated under three conditions, namely generator outage, line outage, and both outage in IEEE 118 and IEEE 30 bus-systems. In the IEEE 30 bus system, TCSC provides better security of 1.4 severity at normal conditions and 1.3 severity in contingency conditions. In the IEEE 118 bus system, UPFC has less severity of 2.4 at normal conditions, and STATCOM has the least severity of 3 at contingency conditions. The proposed model provides enhanced security in all circumstances and reduces overall costs.

Detecting the human operator's cognitive state is paramount in settings wherein maintaining optimal workload is necessary for task performance. Blink rate is an established metric of cognitive load, with a higher blink frequency being observed under conditions of greater workload. Measuring blink rate requires the use of eye-trackers which limits the adoption of this metric in the real-world. The authors aim to investigate the effectiveness of using a generic camera-based system as a way to assess the user's cognitive load during a computer task. Participants completed a mental task while sitting in front of a computer. Blink rate was recorded via both the generic camera-based system and a scientific-grade eye-tracker for validation purposes. Cognitive load was also assessed through the performance in a single stimulus detection task. The blink rate recorded via the generic camera-based approach did not differ from the one obtained through the eye-tracker. No meaningful changes in blink rate were however observed with increasing cognitive load. Results show the generic-camera based system may represent a more affordable, ubiquitous means for assessing cognitive workload during computer task. Future work should further investigate ways to increase its accuracy during the completion of more realistic tasks.

As a fundamental function, lane following plays an important role for driverless vehicles. Unfortunately, lane followers generally confront great difficulty in lane line missed situations caused by vague line, shadows etc. However, for most lane line missed situation, clues of the line may be hidden in prior view of it. Consequently, a lane follower called UNL Lane Follower, which contains two deep learning network modules is proposed. The first module is a lane line detection model called UNET_CLB. Here, the sequence of image frames is utilised rather than only the current frame to deal with the missing lane lines. The second module is a lane-following model called LSTM_DTS, which combines a deep learning attention mechanism (temporal attention network and spatial attention network) with a recurrent neural network. As a result, the proposed UNL Lane Follower produces smoother driving behaviour, especially when a lane line is temporally missed. For better explain ability, the role of each part of the network structure is analysed and explained intuitively. As a modularised network, the UNET_CLB is firstly trained and tested on the TuSimple dataset and CULane dataset. The LSTM_DTS lane follow is then trained and tested on our actual lane following dataset. Finally, the UNL Lane Follower is trained and tested as a whole in a simulation running on Webots, after importing the weight of the two modules trained separately. All testing results showed that the UNL Lane Follower can provide better robustness and accuracy for lane line following mission in the line missed situations.

The authors present the investigation of a new hybrid predictive model of Duplex Attention-based Coupled LSTM Markov Averaged Neural Network, known as DACLMANN. The financial field, particularly the stock market, heavily relies on accurate predictive models. DACLMANN comprises four essential components: two LSTM blocks, an Averagiser and a Markov Neural Network block. The first LSTM block is composed of two hidden layers, each containing 50 neurons and a dense layer with 25 neurons. The second LSTM block consists of two hidden layers, each with 100 neurons, and a dense layer with 50 neurons. The Averagiser plays a crucial role by averaging the closing prices and predicted values from the first LSTM block, resulting in a 90% gain. These averaged values are then fed into the second LSTM block for further prediction. Finally, the predictions undergo evaluation using the Markov model, yielding the final prediction. To assess the performance of DACLMANN, it was tested on 22 years of stock prices for the AMZN index. The evaluation metrics used by the authors include an R2 of 0.76, mean absolute error of 6.81216, root mean square error of 8.6040, Precision of 1, Accuracy of 1, Recall of 1 and F1 of 1. Additionally, DACLMANN achieved a Mean Absolute Percentage Error of less than 0.043% and an RMSPE of less than 2.1%. These results not only demonstrate the effectiveness of the proposed model but also authenticate the prediction outcomes. DACLMANN offers several advantages over traditional predictive models in the stock market. By combining the strengths of Duplex Attention-based Coupled LSTM, Averagiser, and Markov Neural Network, DACLMANN leverages the power of deep learning, attention mechanisms, and sequential modelling. This hybrid approach enables DACLMANN to capture intricate patterns and dependencies present in stock market data, leading to more accurate and reliable predictions. The robust evaluation metrics further validate the superiority of DACLMANN in predicting stock prices.

Self-reflection practice in coaching can help with time management by promoting self-awareness. Through this process, a coach can identify habits, tendencies and behaviours that may be causing distraction or make them less productive. This insight can be used to make changes in behaviour and establish new habits that promote effective use of time. This can also help the coach to prioritise goals and create a clear roadmap. An AI powered system has been proposed that maps the conversion onto topics and relations that could help the coach with note-taking and progress identification throughout the session. This system enables the coach to actively self-reflect on time management and make sure the conversation follows the target framework. This will help the coach to better understand the goal setting, breakthrough moment, and client accountability. The proposed end-to-end system is capable of identifying coaching segments (Goal, Option, Reality, and Way forward) across a session with 85% accuracy. Experimental evaluation has also been conducted on the coaching dataset which includes over 1k one-to-one English coaching sessions. In regards to the novelty, there are no datasets of such nor study of this kind to enable self-reflection actively and evaluate in-session performance of the coach.

Machine vision in low-light conditions is a critical requirement for object detection in road transportation, particularly for assisted and autonomous driving scenarios. Existing vision-based techniques are limited to daylight traffic scenarios due to their reliance on adequate lighting and high frame rates. This paper presents a novel approach to tackle this problem by investigating Vehicle Detection and Localisation (VDL) in extremely low-light conditions by using a new machine learning model. Specifically, the proposed model employs two customised generative adversarial networks, based on Pix2PixGAN and CycleGAN, to enhance dark images for input into a YOLOv4-based VDL algorithm. The model's performance is thoroughly analysed and compared against the prominent models. Our findings validate that the proposed model detects and localises vehicles accurately in extremely dark images, with an additional run-time of approximately 11 ms and an accuracy improvement of 10%–50% compared to the other models. Moreover, our model demonstrates a 4%–8% increase in Intersection over Union (IoU) at a mean frame rate of 9 fps, which underscores its potential for broader applications in ubiquitous road-object detection. The results demonstrate the significance of the proposed model as an early step to overcoming the challenges of low-light vision in road-object detection and autonomous driving, paving the way for safer and more efficient transportation systems.

Wireless sensor network have also played a vital role in the observation and management of agricultural land in terms of climate, water usage, crops, etc. Due to the open communication system and low battery power of sensors, the agricultural sector still faces issues with energy consumption, information forwarding, and privacy. Thus, an energy-efficient routing during transmission in WSN-based smart agriculture is suggested in this study applying a feed-forward neural network to detect outliers. Outlier identification, CH-selection, and Relay Node (RN) selection are the three phases of this suggested method. Outlier detection is performed in the deployed nodes for categorises attack nodes from the normal nodes. CH-selection is performed using a chaotic moth-flame optimization technique according to distance, node degree, centrality factor and residual energy level, these parameters determine which node will become a Cluster Head. Then reliable routing protocol is designed using NB-based probability method for RN selection. MATLAB software is used to test the proposed Outlier Detection based Energy Efficient and Reliable Routing Protocol and verify its performance. The effectiveness of the proposed-model is tested with some prior wireless sensor network routing protocols environment-fusion multipath routing protocol, dynamic Multi-hop Energy Efficient Routing Protocol, SEMantic CLustering, and Reliable and energy efficient routing protocol. Outlier Detection based Energy Efficient and Reliable Routing Protocol algorithm attained a 0.91 (%)Packet Delivery ratio, 0.08% of packet loss, 0.91% of Average residual energy, 2.8 (Mbps) throughput, and 26 (sec) Delay.