Journal of Information Systems and Telecommunication
Volume:10 Issue: 1, Jan-Mar 2022

Nowadays, social media platforms have become a mirror that imitates opinions and feelings about any specific product or event. These product reviews are capable of enhancing communication among entrepreneurs and their customers. These reviews need to be extracted and analyzed to predict the sentiment polarity, i.e., whether the review is positive or negative. This paper aims to predict the human sentiments expressed for beauty product reviews extracted from Amazon and improve the classification accuracy. The three phases instigated in our work are data pre-processing, feature extraction using the Bag-of-Words (BoW) method, and sentiment classification using Machine Learning (ML) techniques. A Global Optimization-based Neural Network (GONN) is proposed for the sentimental classification. Then an empirical study is conducted to analyze the performance of the proposed GONN and compare it with the other machine learning algorithms, such as Random Forest (RF), Naive Bayes (NB), and Support Vector Machine (SVM). We dig further to cross-validate these techniques by ten folds to evaluate the most accurate classifier. These models have also been investigated on the Precision-Recall (PR) curve to assess and test the best technique. Experimental results demonstrate that the proposed method is the most appropriate method to predict the classification accuracy for our defined dataset. Specifically, we exhibit that our work is adept at training the textual sentiment classifiers better, thereby enhancing the accuracy of sentiment prediction.

In this paper, the performance of meta-heuristic algorithms is compared using statistical analysis based on new criteria (powerfulness and effectiveness). Due to the large number of meta-heuristic methods reported so far, choosing one of them by researchers has always been challenging. In fact, the user does not know which of these methods are able to solve his complex problem. In this paper, in order to compare the performance of several methods from different categories of meta-heuristic methods new criteria are proposed. In fact, by using these criteria, the user is able to choose an effective method for his problem. For this reason, statistical analysis is conducted on each of these methods to clarify the application of each of these methods for the users. Also, powerfulness and effectiveness criteria are defined to compare the performance of the meta-heuristic methods to introduce suitable substrate and suitable quantitative parameters for this purpose. The results of these criteria clearly show the ability of each method for different applications and problems.

These days, heart illnesses are viewed as the essential purposes behind unforeseen passing. Along these lines, different clinical gadgets have been created by designers to analyze and examine different infections. Clinical consideration has gotten one of the main issues for the two individuals and government considering enthusiastic advancement in human people and clinical use. Numerous patients experience the ill effects of heart issues making some basic dangers their life, consequently they need ceaseless observing by a conventional checking framework for example, Electrocardiographic (ECG) which is the main procedure utilized in estimating the electrical movement of the heart, this method is accessible just in the emergency clinic which is exorbitant and far for distant patients. The improvement of far-off advancements enables to develop an association of related devices by methods for the web. The proposed ECG checking framework comprises of AD8382 ECG sensor to peruse patient's information, Arduino Uno, ESP8266 Wi-Fi module, and site page. The usage of the proposed ECG medical care framework empowers the specialist to screen the patient's distantly utilizing IoT http application library utilized in Arduino ide compiler to such an extent that it can send that information to website page made, on imagining the patient's ECG signal without human presence site page itself can book arrangement for that persistent, if it is anomalous. The observing cycle should be possible at whenever and anyplace without the requirement for the emergency clinic.

The wireless sensor network (WSN) signifies to a gathering of spatially spread and committed sensors for observing and logging the physical states of the environment and for organizing the information gathered at the central Base station. Many security threats may affect the functioning of these networks. Security of the data in the system depends on the cryptographic procedure and the methods where encryption and decryption keys are developed among the sensors. Symmetric key foundation is one of the best applicable ideal models for safe exchanges in WSNs. The main goal is to improve and evaluate certain issues, such as node attack, to provide better key strength, connectivity, security for node interaction, and throughput. Uniform Balanced Incomplete Block Design (UBIBD) is used to generate the keys allocated by the base station to the cluster head. The cluster head distributes keys to its members using Symmetric Balanced Incomplete Block Design (SBIBD), and the keys are refreshed on a regular basis to avoid out-of-date entries. In wireless sensor networks, compromised nodes can be used to inject false reports. The concept of interacting between sensor nodes using keys and establishing a secure connection aids in ensuring the network's security.

The Air Traffic Management system is a complex issue that faces factors such as Aircraft Crash Prevention, air traffic controllers pressure, unpredictable weather conditions, flight emergency situations, airplane hijacking, and the need for autonomy on the fly. agent-based software engineering is a new aspect in software engineering that can provide autonomy. agent-based systems have some properties such: cooperation of agents with each other in order to meet their goals, autonomy in function, learning and Reliability that can be used for air traffic management systems. In this paper, we first study the agent-based software engineering and its methodologies, and then design a agent-based software model for air traffic management. The proposed model has five modules .this model is designed for aircraft ,air traffic control and navigations aids factors based on the Belief-Desire-Intention (BDI) architecture. The agent-based system was designed using the agent-tool under the multi-agent system engineering (MaSE) methodology, which was eventually developed by the agent-ATC toolkit. In this model, we consider agents for special occasions such as emergency flights’ and hijacking airplanes in airport air traffic management areas which is why the accuracy of the work increased. It also made the flight’s sequence arrangement in take-off and landing faster, which indicates a relative improvement in the parameters of the air traffic management

Wireless sensor networks include a set of non-rechargeable sensor nodes that interact for particular purposes. Since the sensors are non-rechargeable, one of the most important challenges of the wireless sensor network is the optimal use of the energy of sensors. The selection of the appropriate cluster heads for clustering and hierarchical routing is effective in enhancing the performance and reducing the energy consumption of sensors.

Clustering sensors in different groups is one way to reduce the energy consumption of sensor nodes. In the clustering process, selecting the appropriate sensor nodes for clustering plays an important role in clustering. The use of multistep routes to transmit the data collected by the cluster heads also has a key role in the cluster head energy consumption. Multistep routing uses less energy to send information.

In this paper, after distributing the sensor nodes in the environment, we use a Teaching-Learning-Based Optimization (TLBO) algorithm to select the appropriate cluster heads from the existing sensor nodes. The teaching-learning philosophy has been inspired by a classroom and imitates the effect of a teacher on learner output. After collecting the data of each cluster to send the information to the sink, the cluster heads use the Tabu Search (TS) algorithm and determine the subsequent step for the transmission of information.

The simulation results indicate that the protocol proposed in this research (TLSIA) has a higher last node dead than the LEACH algorithm by 75%, ASLPR algorithm by 25%, and COARP algorithm by 10%.

Given the limited energy of the sensors and the non-rechargeability of the batteries, the use of swarm intelligence algorithms in WSNs can decrease the energy consumption of sensor nodes and, eventually, increase the WSN lifetime.

Deep Learning (DL) is the most widely used image-analysis process, especially in medical image processing. Though DL has entered image processing to solve Machine Learning (ML) problems, identifying the most suitable model based on evaluation of the epochs is still an open question for scholars in the field. There are so many types of function approximators like Decision Tree, Gaussian Processes and Deep Learning, used in multi-layered Neural Networks (NNs), which should be evaluated to determine their effectiveness. Therefore, this study aimed to assess an approach based on DL techniques for modern medical imaging methods according to Magnetic Resonance Imaging (MRI) segmentation. To do so, an experiment with a random sampling approach was conducted. One hundred patient cases were used in this study for training, validation, and testing. The method used in this study was based on full automatic processing of segmentation and disease classification based on MRI images. U-Net structure was used for the segmentation process, with the use of cardiac Right Ventricular Cavity (RVC), Left Ventricular Cavity (LVC), Left Ventricular Myocardium (LVM), and information extracted from the segmentation step. With train and using random forest classifier, and Multilayer Perceptron (MLP), the task of predicting the pathologic target class was conducted. Segmentation extracted information was in the form of comprehensive features handcrafted to reflect demonstrative clinical strategies. Our study suggests 92% test accuracy for cardiac MRI image segmentation and classification. As for the MLP ensemble, and for the random forest, test accuracy was equal to 91% and 90%, respectively. This study has implications for scholars in the field of medical image processing.

Before the advent of the World Wide Web, lack of information was a problem. But with the advent of the web today, we are faced with an explosive amount of information in every area of search. This extra information is troublesome and prevents a quick and correct decision. This is the problem of information overload. Multi-document summarization is an important solution for this problem by producing a brief summary containing the most important information from a set of documents in a short time. This summary should preserve the main concepts of the documents. When the input documents are related to a specific domain, for example, medicine or law, summarization faces more challenges. Domain-oriented summarization methods use special characteristics related to that domain to generate summaries. This paper introduces the purpose of multi-document summarization systems and discusses domain-oriented approaches. Various methods have been proposed by researchers for multi-document summarization. This survey reviews the categorizations that authors have made on multi-document summarization methods. We also categorize the multi-document summarization methods into six categories: machine learning, clustering, graph, Latent Dirichlet Allocation (LDA), optimization, and deep learning. We review the different methods presented in each of these groups. We also compare the advantages and disadvantages of these groups. We have discussed the standard datasets used in this field, evaluation measures, challenges and recommendations.