International Journal of Advanced Intelligence Paradigms (23 papers in press)

Regular Issues

• CUSTOMER REVIEW SUMMARIZATION BASED ON GENERIC WRAPPER AND OPINION MINING  
  by K. Priya, K. Dinakaran 
  Abstract: Now-a-days onine shopping by customers is getting increased day by day. Customers are having awareness in the case of buying products based on the features of the products. The features of the product may be model, colour, size, Durability or price.The customer reviews or feedbacks based on the price of the products are collected from three different shopping websites and then consolidated and also ranked under separate website.The customer will be buying the product based on lowest price ,which online shopping website is holding.Through this work customer can avoid confusion while shopping for products.Generic wrapper and VIPS techniques are used.These details can also be posted or shared in social networks webpages for customers convenience.Then the customers can maintain budjet and preventing them from taking wrong decision during online shopping.Searching Time for product information under each website can be reduced for the customers.
  Keywords: Generic wrapper; Wrapper Generation; product review; social network; Review Summarization; E-Commerce.
  DOI: 10.1504/IJAIP.2021.10030025
   
  
• A Novel Variant of Bat Algorithm Inspired from CATD-Pursuit Strategy & Its Performance Evaluations  
  by Shabnam Sharma, Sahil Verma, Kiran Jyoti 
  Abstract: This paper presents a novel nature inspired optimization technique, which is a variant of Standard Bat Algorithm. This optimization technique is inspired from the pursuit strategy of microchiroptera bats and their efficient way of adaptation according to dynamic environment. Here dynamic environment describes different movement strategies adopted by prey (target), during their pursuit. Accordingly, bats have to adopt different pursuit strategies to capture the prey (target). In this research work, a variant of Bat Algorithm is proposed considering the pursuit strategy Constant Absolute Target Detection (CATD), adopted by bats, while targeting preys moving erratically. The proposed algorithm is implemented in Matlab. Results obtained are validated in comparison to Standard Bat Algorithm on the basis of best, mean, median, worst and standard deviation. The results demonstrate that the proposed algorithm provides better exploration and avoid trapping in local optimal solution.
  Keywords: Bat Algorithm; Constant Absolute Target Detection (CATD); Computational Intelligence; Echolocation; Meta-heuristic; Nature-Inspired Intelligence; Optimization; Pursuit Strategy; Swarm Intelligence.
  DOI: 10.1504/IJAIP.2021.10030248
   
  
• Wireless Smart Automation Using IOT Based Raspberry Pi  
  by Vasu Goel, Akash Deep, Madireddy Vivek Reddy, Yedukondala Rao Veeranki 
  Abstract: In this paper we propose a smart door lock system and lighting system for home automation. This door lock system and lighting system is controlled by Radio Frequency Identification (RFID) reader which is programmed by Raspberry Pi to detect the input swipe through our university combo card or a RFID tag and wirelessly sends the signal to the Espruino (ESP) Wi-Fi module and Node Microcontroller Unit (MCU) which in turn activates the lighting system and door lock system. The mainstream application of the system will be in hostel rooms or in our homes wherever door locks are there so that doors can be opened anytime we want without disrupting our work or getting up from our places in case of any injury with a swipe of card
  Keywords: Internet-Of-Things; Raspberry pi; Radio-Frequency Identification; Home automation; MQTT.
  DOI: 10.1504/IJAIP.2019.10026853
   
  
• VLSI Implementation of ECG Feature Extraction: A Literature Review  
  by Surendhar S, Thirumurugan P, Ezhilmathi N, Sathesh Raaj R 
  Abstract: In this paper, we examine the comparative learning on VLSI Implementation of Electrocardiogram (ECG) feature extraction method to diagnose the different cardiac arrhythmia. ECG features extraction plays an important significant role in diagnosing most of the cardiac diseases to avoid mortality. In ECG, P-QRS-T wave generated using some novel method to find the peak amplitude and time periods. Recently different methods have been implemented in VLSI for analyzing the ECG signal by multiple researchers. Several techniques and algorithms comprise their own merits and demerits. In this paper, the various methods and techniques are discussed in literature review for cardiac analysis.
  Keywords: Area; Detection Error Rate; Delay; ECG signal; Feature Extraction; Power and Support Vector Machines.
  
  
• Comparative Study of Kernel Algorithms On SIMD Vector Processor for 5G Massive MIMO  
  by Ravi Sekhar Yarrabothu, Pitchaiah Telagathoti 
  Abstract: Currently world is moving towards achieving Gigabit data rates via 5G mobile revolution. Massive Multi-In-Multi-Out (MIMO) is one of the key enabler and recently lot of interest is evinced in this area. The efficiency of the algorithms to estimate and detect the channel plays a very crucial role for the success of Massive MIMO. The existing algorithms of LTE-A for this purpose are not efficient in terms of power consumption and lower latency, which is one of the foremost necessity of 5G communications. The biggest hurdle to achieve the ultra-low latency in 5G massive MIMO is - a very huge number of computations required for the matrix inversion while performing channel estimation and detection. In this paper, a comparative study has been done for two parallel processing schemes: Gauss-Jordan elimination and LU decomposition kernel algorithms on a single instruction multiple data (SIMD) stream vector processor for the realization of matrix inversion with optimum latency, which is the pre-requisite for the 5G channel estimation and detection. In this paper both matrix inversion algorithms Gauss Jordan and LU decomposition are analyzed and LU decomposition provides the required level of reduction of computational operations, which translates low latency and less battery power consumption.
  Keywords: Massive MIMO; SIMD; 5G ; DMRS; SRS; LTE - A.
  DOI: 10.1504/IJAIP.2024.10066835
   
  
• Data Mining Techniques and Fuzzy Logic to Build a Risk Prediction System for Stroke  
  by Farzana Islam, M. Rashedur Rahman 
  Abstract: Nowadays, by using different computational system medical sector predict diseases. These systems not only aid medical experts but also normal people. In recent years stroke becomes life threatening deadly cause and it increased at global alarming state. Early detection of stroke disease can be helpful to make decision and to change the lifestyle of people who are at high risk. There is a high demand to use computational expertise for prognosis stroke. Research has been attempted to make early prediction of stroke by using data mining techniques. This paper proposes rule based classifier along with other techniques. The dataset is collected from Dhaka medical college, situated in Dhaka, Bangladesh To build a more accurate and acceptable model the system uses different classification methods likely- Decision tree, Support vector machine, Artificial neural network and fuzzy model. K-means, EM and fuzzy C-means clustering algorithm are used to label the dataset more accurately. Fuzzy inference system is also built to generate rules. ANFIS provides the most accurate model.
  Keywords: stroke; decision tree; SVM; MLP; artificial neural network; support vector machine; fuzzy model; FIS; ANFIS; data-mining; fcm; clustering; EM clustering; k-means; Bangladeshi dataset; fuzzy rule.
  DOI: 10.1504/IJAIP.2021.10054275
   
  
• Clustering Related Behavior of Users by the use of Partitioning And Parallel Transaction Reduction Algorithm  
  by Thava Mani C, Rengarajan A 
  Abstract: High-speed development of information in associations in the present universe of business exchanges, broad information preparing is a main issue of Information Technology. Generally, an Apriori calculation is broadly used to discover the incessant thing sets from database. Later downside of the Apriori calculation is overwhelmed by numerous calculations yet those are likewise wasteful to discover visit thing sets from expansive database with less time and with awesome productivity. Henceforth another design is proposed which comprises of coordinated conveyed and parallel processing idea. The experiments are conducted to find out frequent item sets on proposed and existing algorithms by applying different minimum support on different size of database. With increased data set, Apriori gives poor performance as compared to proposed Partitioning and Parallel Transaction Reduction Algorithm (PPTRA). The implemented algorithm shows the better result in terms of time complexity and also handle large database with more efficiency.
  Keywords: Pre-processing; Mining of Association rules; frequent item sets; parallel; Apriori; matrix; minimum support; Partitioning.
  
  
• An optimized fuzzy edge detector for image processing and their use in modular neural networks for pattern recognition  
  by Isidra Espinosa-Velazquez, Patricia Melin, Claudia Gonzalez, Frumen Olivas 
  Abstract: In this paper, the development of a fuzzy edge detector optimized with the metaheuristics: Genetic Algorithms and Particle Swarm Optimization is presented, based on the sum of differences method, using as inputs the absolute values of the difference from the pixels in the image. The Pratts figure of merit metric was used to know the performance of the proposed fuzzy edge detector. A modular neural network was designed for the recognition of faces in benchmark images and comparisons were made with different works carried out with other fuzzy edge detection systems. The main contribution of this research work is the development of a new fuzzy edge detector method optimized.
  Keywords: fuzzy logic; fuzzy edge detector; optimization; GA; genetic algorithm; PSO; Particle swarm Optimization; Neural networks.
  
  
• A Study of Feature Reduction Techniques and Classification for Network Intrusion Detection  
  by Meenal Jain, Gagandeep Kaur 
  Abstract: The size of network data increasing tremendously, as the web technologies are emerging day by day. This huge amount of data contains large number of attributes which need to be analyzed for particular application. To analyze the significance of such attributes, different feature reduction techniques can be used. In this paper, three feature reduction techniques such as, Principal Component Analysis (PCA), Artificial Neural Network (ANN), and Nonlinear Principal Component Analysis (NLPCA) have been used to analyze the significance of such attributes. Three newly reduced datasets from the original benchmark dataset Coburg Intrusion Detection Data Set (CIDDS-2017), have been created after applying the above techniques. Four supervised learning based classifiers, namely, Decision Tree (DT), K Nearest Neighbor (KNN), Support Vector Machine (SVM), and Na
  Keywords: Principal Component Analysis; Artificial Neural Network; Nonlinear Principal Component Analysis; Decision Tree; K Nearest Neighbor; Support Vector Machine; Naive Bayes; Sensitivity_Mismatch_Measure; Specificity_Mismatch_Measure; Information_ gain.
  
  
• Adapted Rank Order Clustering-based Test Case Prioritization for Software Product Line Testing  
  by Satendra Kumar, Raj Kumar, Ashish Saini, Monika Rani 
  Abstract: Software Product Line Testing (SPLT) is a strenuous task due to the explosion of derivable products. It is infeasible to test all the products of a Software Product Line (SPL) so, several contributions have been presented to overcome this issue by reducing the number of products. However, not much consideration has been given to the test order of the products. Test Case Prioritization (TCP) technique arranges the test cases in a sequence to meet a specific performance goal. TCP is required to increase the effectiveness and efficiency of fault detection. In SPL, TCP technique arranges the configurations of products in order to be tested. Adapted Rank Order Clustering (AROC)-based TCP approach is proposed for SPLT. Our AROC method utilizes Binary Weight and Decimal Weight to arrange the products of an SPL. The results of the rigorous experimentation using AROC-based TCP approach are better than the random order and similarity-based order in terms of fault detection rate.
  Keywords: Software Product Line Testing (SPLT); Test Case Prioritization (TCP); Rank Order Clustering; Feature Model.
  
  
• EDC-LISP: An Efficient Divide-and-Conquer Solution to The Longest Increasing Subsequence Problem  
  by Seema Rani, Dharmveer Singh Rajpoot 
  Abstract: The Longest Increasing Subsequence problem was initially viewed as an example of a dynamic approach and its major applications include the process of aligning whole genome sequences. We are presenting an optimal solution for the LIS problem using a modified divide-and-conquer approach with o(n log n) time complexity. The proposed method is more efficient and simpler than the earlier LIS solutions using D&C approach. Our approach does not require sorted data and it is more efficient and better than a sequential approach as we can solve the problem by dividing it into smaller subproblems. During the division phase, we do not need any prior knowledge about the length of the LIS the division process is simple and is independent of the type and range of the input sequence and the 'LIS'. We have implemented the proposed approach in C language using input sequences of different lengths ranging from 10 to 100000 elements.
  Keywords: Longest Increasing Subsequence (LIS); Modified Divide-and-Conquer (MD&C); First Row of Young Tableaux (FRYT); First Subproblem (FSP1); Second Sub-problem (SSP2).
  DOI: 10.1504/IJAIP.2021.10048282
   
  
• PEBD: Performance Energy Balanced Duplication Algorithm for Cloud Computing  
  by Sharon Priya Surendran, Aisha Banu W 
  Abstract: With the increasing demand of cloud data, efficient task scheduling algorithms are required with minimal power consumption. In this paper, the Performance-Energy Balanced Duplication (PEBD) scheduling approach is proposed for energy conservation at the point of task duplication. Initially, the resources are preprocessed with the Manhattan distance based Fuzzy Clustering (MFC).Then resources are scheduled using a Novel duplication aware fault tolerant based League-BAT algorithm and faults expected during job executions can be handled proactively. The fault adaptive firefly optimization is used for minimizing faults and it keeps information about resource failure. Consequently, the optimization ensures that performance is improved with the help of task duplication with low energy consumption. The duplications are restricted and they are strictly forbidden if they provide significant enhancement of energy consumption. Finally, enhanced compress & Join algorithm is used for efficient compression processing. It considers both schedule lengths and energy savings to enhance the scheduling performance with less power consumption. The performance of energy consumption and makespan for the proposed approach is increased with 6% and 0.5 % respectively
  Keywords: Manhattan distance; Fuzzy clustering; Resource scheduling; Duplication; fault tolerance; energy conservation.
  
  
• Friend discovery based on user's interest  
  by Kapil Sharma, Sachin Papneja, Nitesh Khilwani 
  Abstract: With the dawn of Web2.0 and Ontological semantic networks, Social Networking Platform popularity and usage has increased dramatically and has been a new area of research for both researchers and academician. Friend Recommendation, which is the one of the indispensable feature of Social media, has taken it to new height. Facebook, Twitter, LinkedIn, MySpace have captivated millions of users now a days. But the antecedent research work on Friend Recommendation cynosure on user current relation in Social Networking. Facebook, one of the most prominent social networking platforms provides the personalized friend recommendation based on FOAF (Friend of a Friend) ontology. MySpace is based on PYMK (People You May Know) friend recommendation. Basic perception behind it is that probability of a person knowing a friend of friend is more than unknown person. This Paper proffers a unique approach of friend recommendation based on the users interest and based on user current location. The main challenge with friend recommendation based on user interest is that user interest keeps on changing. To overcome this challenge, we have proposed recommendation System using Ontology and Spreading Activation. User interest is being captured using the Spreading Activation. Spreading Activation has been used to overcome variation in user interest. Our experimental results have shown the benefits of considering Spreading activation and ontology in friend recommendation in as social networking.
  Keywords: Ontology; Spreading Activation; Social Networking; Friend Recommendation.
  DOI: 10.1504/IJAIP.2022.10035628
   
  
• L(2,2,1)-labelling problems on square of path  
  by S.K. Amanathulla, Madhumangal Pal 
  Abstract: $L(p,q)$-labeling problem is a well studied problem in the last three decades for its wide application, specially in frequency assignment in (mobile) communication system, $X$-ray crystallography, coding theory, radar, astronomy, circuit design etc. $L(2,2,1)$-labeling is an extension of $L(p,q)$-labeling is now becomes a well studied problem due to its application. Motivated from this point of view, we consider $L(2,2,1)$-labeling problem for squares of paths.rnrnLet $G=(V, E)$ be a graph. The $L(2,2,1)$-labeling of the graph $G$ is a mapping $eta:Vrightarrow {0,1,2,ldots}$ so thatrn$'eta(x)-eta(y)'geq 2$ if $d(x, y)=1$ or $2$, $'eta(x)-eta(y)'geq 1 $ if $d(x, y)=3$, where $V$ is the vertex set and $d(x, y)$ is the distance (i.e. minimum number of edges in the shortest path between $x$ and $y$) between the vertices $x$ and $y$. $lambda_{2,2,1}(G)$ is the $L(2,2,1)$-labeling number of $G$, which is the the largest non-negative integer which is used to label the graph $G$. In labeling problems of graph the main target is to find the exact value of $lambda_{2,2,1}(G)$ or to minimize it.rnrn In this paper we have studied $L(2,2,1)$-labeling of squares of paths and obtain a good result for it. rn Also a labeling procedure is presented to label a square of paths. The result of this paper is exact and also it is unique. This is the first result about $L(2,2,1)$-labeling of squares of paths.
  Keywords: Frequency assignment; L(2; 2; 1)-labeling; squares of paths.
  DOI: 10.1504/IJAIP.2022.10034134
   
  
• Improving Mobile Phone Payment Apps Security with QR Code Security  
  by Rijwan Khan, Shadab Ansari 
  Abstract: Nowadays, use of smartphones is increasing at a very fast rate. These phones have the capabilities of a small computers with the ease of doing almost all the tasks with a touch. In this way people will not be depend on the cash flow of money. Simple digital transactions will be there in place of cash flow. One of the major recent development in mobile phones is development of mobile banking systems, wallet systems and third-party payment applications. As the digital currency is now being widely used in market, there are a lot of mobile based application developed for digital payments. Almost all the banks are launching their apps with online payment options along with other facilities for their customers. In addition, there are some other players in market who are launching their mobile application based on wallets for such payments. In developing countries like India, digital payment plays a very important role in boosting the economy. Digital payments has shown a remarkable increase from year 2015 onward in India. In this paper, the authors have proposed a method for security testing of these applications. If an app is more secure, it gives a confidence to the users and will result in more users using this app. The QR code contains the details about the payer or payee and is extensively used by the current payment or wallet systems. Authors have proposed a method for securing the QR code security in mobile payment applications.
  Keywords: Mobile Security (MS); Visual Cryptography (VC); Mobile Payment (MP); Cyber Security (CS); Asymmetric Encryption (AE).
  
  
• Energy-Aware Multi-Objective Job Scheduling in Cloud Computing Environment with Water Wave Optimization  
  by Hima Bindu G B, T. Sunil Kumar Reddy 
  Abstract: Job scheduling is the process of assigning the jobs to the virtual machine based on their operations is sequential manner. Each operation is composed of set of instructions and has variable completion time. Virtual machines can execute single job at a time and the preemption is not possible at the time of job execution. Therefore, scheduling the job to the appropriate resource is a crucial task in cloud computing. Hence this paper intends to develop an advanced JSP in cloud environment using an enhanced water wave optimization (WWO) algorithm known as Control adaptive based WWO (CAP - WWO). Moreover the proposed scheme is compared with conventional algorithms and the results proved the efficiency of the proposed algorithm.
  Keywords: Job - shop scheduling; WWO; Execution time; Utilization rate; Throughput; Makespan.
  
  
• ANALYSIS OF TURBOSHAFT ENGINE-LOW POWER MARGIN  
  by Sasindra Reddy Dappili, Pavan Kumar Kosaraju, Mani Kanta Yetukuri, Prasanna Sai Bodduluri, E.T. Chullai 
  Abstract: Lower power margin is the most commonly occurred problem in turbo shaft engines which are used in helicopters. It is caused due to heavy taintings in air path which leads to fouling. This also leads to reduced air flow of compressor which results in lower power; few more reasons for lower power is damage of hot core components like power turbine blades and impeller. Low power margin is defined as reduction of output shaft power below the minimum required power to lift the helicopter. The engine encountered with low power is confirmed by pilot by measuring the torque with corresponding to altitude and ambient temperature. If the result is not coordinating with the requirements then engine is sent to test bed to find out the problem. The low power snag is confirmed by testing the engine in test bed, if power loss is within the acceptable limit then compressor wash is carried out through which 25% to 35% power is regained. After compressor wash if power is not regained then the engine is sent to Repair and Overhaul division where snag is rectified and sent back to test bed for final analysis. If engine regains the power, then the engine will be dispatched. The engine performance is analyzed through graphs mainly Power vs RPM. During testing, the parameters like power, mass flow rate, delta pressure, GG rpm, PT rpm, ambient temperature etc. are calibrated in test bed using FADEC system. In this paper we compare the power losses due to power turbine blade life cycle completion, impeller damage and chipping of blades found on axial compressors, rectification of snags, procedure followed to rectify the snags, final engine performance comparison and to confirm which snag because more power loss.
  Keywords: Turboshaft ,Compression Fouling; Corrosion ; Engine Testing.
  
  
• Advanced Redistribution Meta Storage Algorithm for Securing Big Data in Cloud computing  
  by Akkipogu Vineela, N. Kasiviswanath, Shoba Bindu C. 
  Abstract: In the recent years, Big Data is one of the emerging fields to process the huge volumes of data. However, it faces lot of challenges in terms of security and storage. Implementing cloud computing with big data enriches the security and storage. A secure architecture is required to manage the big data in cloud. This paper proposed architecture for securing the big data using Advanced RedistributiOn MetA storage (AROMA) algorithm. The importance of the proposed approach is to provide Security-as-a-Service for big data storage. The major issue solved by the proposed approach is restricting the cloud service providers from directly accessing the users data. The experimental setup is conducted in the Amazon EC2 environment. The results proved the efficiency of the proposed method.
  Keywords: Big Data; Cloud; Security; Encryption; Storage.
  
  
• Load-balanced Multilayered Clustering Protocol to Maximize the Lifetime of Wireless Sensor Networks  
  by Rohan Gupta, Arnab Nandi 
  Abstract: This article introduces an innovative clustering protocol for load balancing in Wireless Sensor Networks (WSNs). In the proposed protocol, square shape clusters of equal area are arranged in a multilayer fashion, and the base station is at the center of the network. The equal area of square clusters offers a nearly equal number of member nodes in each cluster which leads to comparable energy consumption at cluster heads for transmitting and receiving data from member nodes. This article also introduces a new routing approach in which hop selection is based on the difference of angle between the source and destination cluster heads with respect to a particular point. The efficiency of the proposed protocol concerning network lifetime and energy consumption is evaluated and compared with Low-Energy Adaptive Clustering Hierarchy (LEACH), Enhanced-Modified LEACH (E-MODLEACH) and Least Distance clustering (LDC). The efficiency of the proposed protocol is also evaluated for different optimization algorithms like GWO, PSO, and GSA. The proposed protocol is implemented with these algorithms during the cluster formation stage.
  Keywords: WSN; Clustering Protocol; Load Balancing; Network Lifetime; GWO; PSO; GSA; LEACH; E-MODLEACH; LDC.
  
  
• Case-Based Reasoning Methodology for eLearning Recommendation System  
  by Swati Shekapure, Dipti D. Patil 
  Abstract: Increasingly, eLearning has become a leading development trend in the industry. As far as the learning methodology is concerned, it has been observed that traditional learning methods such as teacher and student, chalk and duster have turned to modern & innovative learning. Due to a revolution in technology, everyone started learning by using the internet. They have been using devices like smartphones, laptops, e-books, I-pod and so on for gaining instructions. So, while they procure the learning they admit certain records, which are not significant to answer all their exploratory questions. Ultimately, there was a huge delay while scrutinizing the essential material on the internet, so there was an extremity to customize the search by acquiring certain information of a user to improve the search quality and save time. The recommended eLearning system is a case based system using a case-based reasoning approach and a distinct classification algorithmic rule to categorize the students learning interest. This system assembles student's learning preferences from a distinct discussion and systematically categorizes that characteristic into a learning standard.
  Keywords: Case-Based Reasoning; K Nearest Neighbor; Learning Style; Recommendation system.
  DOI: 10.1504/IJAIP.2022.10035296
   
  
• A Community Based Trusted Collaborative Filtering Recommender Systems Using Pareto Dominance Approach  
  by Anupama Angadi, Satya Keerthi Gorripati 
  Abstract: Recommender System algorithms provided clarification to information overload problem suffered by netizens. The Collaborative Recommender Filtering approach takes the user-item rating matrix as an input and recommends items based on the perceptions of similar neighbours. However, sparsity issue in the rating matrix leads to untrustworthy predictions. However, the conventional Collaborative Recommender Filtering method chooses ineffective descriptive users as neighbours for each target user. This hints that the recommendations made by the system remain inaccurate. The proposed approach addresses this issue by applying a pre-filtering process and integrates community detection with Pareto dominance, which considers trusted neighbours from the community into which the active user pertains and eliminates dominant users from the neighbourhood. The results on the proposed framework showed a noteworthy improvement in all the accuracy measures when related to the traditional approaches.
  Keywords: Community Detection; Recommender Systems; Sparsity; Pareto dominance; Cold Start; Trust propagation;.
  
  
• DOCUMENT SUMMARIZATION USING RECURRENT NEURAL NETWORK  
  by Vijayakumar K, Dafni Rose J 
  Abstract: Document Summarization is the process which condenses the given document to generate a summary which captures the main essence of the entire document. In recent years, there has been increased interest in automatic summarization. Automatic summarization refers to summarizing a document using software and it helps to reduce large text documents to a short set of words or a paragraph that delivers the main meaning of the full text. The extracted features from the documents are used for the automatic summarization process and remain a successfully proven approach but it leads to drawbacks with respect to structure, redundancy, coherence. Existing methods for single document summarization usually make use of only the first sentence or fixed number of words from the beginning contained in the specified document. This paper proposes a technique that uses contents of the entire document to provide more knowledge to help single document summarization. The proposed system mainly aims at generating a summary of at least a minimum length unlike the existing system that generates empty summary if it couldnt find the keyword present in the input document which meets the attention weight beyond a threshold. Also, the proposed system is focused in maintaining the structure of the summaries generated for the given document.
  Keywords: text; summarize; document; recurrent.
  
  
• Web Server Workload Prediction using Time Series Model  
  by Mahendra Pratap Yadav, Akanksha Kunwar, Ram Chandra Bhushan, Dharmendra Kumar Yadav 
  Abstract: In distributed systems, multi-tier storage systems and cloud data-centers are used for resource sharing among several clients. To fulfill the clients request, the cloud providers share it's resources and manage the workload, which introduces many performance challenges and issues. One of the main challenges is resource provisioning in virtual machine (VMs or Container) since VMs are subjected to meet the demand of users with different profiles and Quality of Service (QoS). This proactive resource management approach requires an appropriate workload prediction strategy for real-time series data. The time series model exhibits prominent periodic patterns for the workload that evolves from one point of time to another with some short of time in random fluctuation. In this paper, a solution for the prediction of web server load problem has been proposed, which is based on seasonal ARIMA (Autoregressive Integrated Moving Average Model) model. ARIMA is a forecasting technique which predicts the future value based on its inertia. In seasonal ARIMA, seasonal AR and MA are used to predict the value xt (CPU workload time series) with the help of data values and errors at time lags that are multiple to the span of seasonality. We have evaluated our proposed method using real-world web workload data.
  Keywords: Cloud Computing; Elasticity; Auto-scaling; Time Series; Machine Learning.
  DOI: 10.1504/IJAIP.2022.10034175