Journal of Intelligent & Fuzzy Systems - Volume 45, issue 4

Authors: Kirthika, K.M. | Paulraj, M.P. | Hema, C.R.

Article Type: Research Article

Abstract: The EEG-based HTR utilizing AEP responses of both group of participants with normal hearing and abnormal hearing are managed with the objective of detecting hearing sensitivity level using Chebyshev Recurrence Polynomial and Dempster Convolutional Neural Network (CRP-DCNN) is designed. The CRP-DCNN method is split into three sections. They are preprocessing using Chebyshev Recurrence Polynomial Filter, feature extraction by employing Orthogonalized Singular Value and Median Skewed Wavelet. Here, both Orthogonalized Singular Value Decomposition-based parametric and Median Skewness-based non-parametric modeling techniques are employed for first obtaining the hearing threshold factors and then extracting statistical features for further processing. Finally Dempster Convolutional Neural …Network-based Classification for detecting hearing sensitivity level is presented. Hence, the objective to determine the significant correlations between the brain dynamics and the auditory responses and detect the hearing sensitivity level of the group of participants with normal hearing and with the group of participants with hearing loss are designed on accordance with the features of EEG signals. Simulations are performed in MATLAB to validate the features of EEG signals. Show more

Keywords: Electroencephalogram, hearing threshold response, auditory evoked potential, chebyshev recurrence polynomial, orthogonalized singular value decomposition, median skewness, dempster convolutional neural network

DOI: 10.3233/JIFS-231794

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5353-5366, 2023

Authors: Vaigandla, Karthik Kumar | Benita, J.

Article Type: Research Article

Abstract: Filter Bank Multicarrier(FBMC)is considered as one of the most standardized waveform for fifth generation (5G) mobile communication system application FBMC endures lot of nonlinear effects which occurs because of high Peak Average Power Ratio (PAPR). High value of PAPR due to the large dynamic range of multicarrier signal is one of the most significant issues in FBMC multicarrier based modulation technique. This paper presents one investigated PAPR reduction technique named as Selected Mapping (SLM) to minimize high PAPR by utilizing the complex signal divide into real and imaginary parts and then select minimum PAPR signal based on Modified Forest Optimization …Algorithm (MFOA)to achieve good PAPR which can maintain the FBMC based system performance with a required Bit Error Rate (BER). The associated method was produced with the aim of optimize the phase factors so that the phase rotation operation is accomplished to minimize PAPR by fixing the MFOA into the conventional SLM. The simulation results demonstrate that the proposed technique gives better performance in terms of BER and PAPR compared to other SLM based optimization techniques. Show more

Keywords: Bit error rate, filter bank multicarrier, modified forest optimization algorithm, selected mapping, peak average power ratio

DOI: 10.3233/JIFS-222090

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5367-5381, 2023

Authors: Mansoor, J. Shafiq | Subramaniam, Kamalraj

Article Type: Research Article

Abstract: The usage of cloud-based grid computing services and Internet of Things (IoT) devices in medical diagnoses is increasing enormously. The cloud service provider’s data centers store vast amounts of data without processing it. This big data need some intelligent technique to analyze and classify heart disease from the considerable volume of data; it is a challenging task. Many deep learning techniques are introduced earlier for heart disease diagnosis in the literature study. Still, all other classification techniques failed to achieve the minimum loss in heart disease classification with the highest accuracy and faster performance. This research introduces a new classification …approach to overcome these issues: elephant herding optimizer turned restricted Boltzmann machine EHO-RBM network. The optimizer is used in this network to optimize the number of neuron utilization during the learning process by updating the network weight without compromising the loss. The previous research proves that the optimizer is performed well in reaching global minima efficiently. Therefore, the new classifier incorporates the optimizers instead of the classical stochastic gradient descent optimizer to improve the network performance by minimizing the global minima faster with less loss in predicting heart disease. The simulation result of the new heart disease classification framework shows that the elephant herding optimizer-trained classification model has reduced the loss rate and maximized the accuracy rate up to 0.0027 then the comparison method. As a result, the new classifier has obtained a maximum accuracy of up to 99.96% . Show more

Keywords: Cloud computing, grid computing, IoT devices, elephant search optimizer turned restricted Boltzmann machine network, big data analytics, heart disease

DOI: 10.3233/JIFS-224275

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5383-5399, 2023

Authors: Vennam, Preethi | Mouleeswaran, S.K.

Article Type: Research Article

Abstract: Wireless Sensor Networks (WSNs) are a group of devices/sensors which are connected as a network for transferring and receiving the data observed from the environment through intermediate links. Energy efficiency and security during data broadcasting are considered challenging tasks in the WSN. These challenging tasks are considered as a motivation of this research and the Multi-Objective - Trust Aware Average Inertia Weighted Cat Swarm Optimization (MO-TAIWCSO) is proposed for achieving secure reliable transmission over the WSN. Due to an effective velocity update of searching process, the AIWCSO is selected for discovering an optimal solutions. The developed MO-TAIWCSO is optimized by …using the trust, energy ratio, communication cost, and degree of SCH. This MO-TAIWCSO performs optimal Secure Cluster Head (SCH) and secure path discovery for the secure transmission of data under malicious attacks. The main objective of this MO-TAIWCSO is to improve the data delivery while minimizing the energy usage of the nodes. The performance of the MO-TAIWCSO method is analyzed by using the throughput, Packet Delivery Ratio (PDR), energy consumption, network lifetime, Normalized Routing Load (NRL) and End to end delay (EED). The existing researches namely ETOR and TBSEER are used to evaluate the MO-TAIWCSO. The PDR of MO-TAIWCSO for 100 nodes is 99.97%, which is high when compared to the ETOR and TBSEER. Show more

Keywords: Energy efficiency, malicious Attacks, multi objective-trust aware average Inertia weighted cat swarm optimization, wireless sensor networks

DOI: 10.3233/JIFS-230564

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5401-5408, 2023

Authors: Zhao, Shulin | Sun, Xiaoting | Gai, Lingyun

Article Type: Research Article

Abstract: Plant diseases and pests are primary factors that can negatively affect crop yield, quality, and profitability. Therefore, the accurate and automatic identification of pests is crucial for the agricultural industry. However, traditional methods of pest classification are limited, as they face difficulties in identifying pests with subtle differences and dealing with sample imbalances. To address these issues, we propose a pest classification model based on data enhancement and multi-feature learning. The model utilizes Mobile Inverted Residual Bottleneck Convolutional Block (MBConv) modules for multi-feature learning, enabling it to learn diverse and rich features of pests. To improve the model’s ability to …capture fine-grained details and address sample imbalances, data enhancement techniques such as random mixing of pictures and mixing after region clipping are used to augment the training data. Our model demonstrated excellent performance not only on the large-scale pest classification IP102 dataset but also on smaller pest datasets. Show more

Keywords: Data enhancement, Multi-feature fusion, Pest classification, Convolution neural network

DOI: 10.3233/JIFS-230606

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5409-5421, 2023

Authors: Saurabh, | Sharma, Chirag | Khan, Shakir | Mahajan, Shubham | Alsagri, Hatoon S. | Almjally, Abrar | Alabduallah, Bayan Ibrahimm | Ansari, Asrar Ahmad

Article Type: Research Article

Abstract: With the ever-increasing demand for IoT Devices which enable all objects to connect and exchange information in applications such as healthcare applications, Industry 4.0, smart cities and smart homes, etc. IoT devices play a crucial role in our day-to-day life like homes, offices, healthcare, wearable, and agriculture. With the development of IoT devices, securing device-to-device communication has attracted more and more attention and we need to ensure the privacy and security of data amongst these IoT devices. User authentication has emerged as a major security concern while connecting IoT devices and the cloud. Many authentication schemes like mutual authentication, group …authentication have been proposed to ensure only authenticated users and with very high confidence we can rely on the decision-making process. Symmetric key based as well as Asymmetric key-based solutions have been proposed but due to the resource constraint nature of the IoT devices designing lightweight, robust, provably secure authentication schemes is a big challenge. This paper discusses the various authentication techniques designed for low-powered IoT devices and proposes a lightweight authentication scheme for IoT. Show more

Keywords: IoT, authentication, lightweight, Industry 4.0, and security

DOI: 10.3233/JIFS-232388

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5423-5439, 2023

Authors: Zheng, Yulan

Article Type: Research Article

Abstract: In marketing, customer segmentation is a very critical element. This paper focuses on clustering algorithms. First, the commonly used K-means algorithm was introduced, and then, it was optimized using the improved Lion Swarm Optimization (ILSO) algorithm and the Calinski-Harabasz (CH) index. The results of the experiment for the UCI dataset showed that the CH indicator obtained an accurate number of clusters, and the clustering accuracy of the ILSO-K-means algorithm was higher, both above 90%. Then, in customer segmentation, the customers of an enterprise were divided into four groups using the ILSO-K-means algorithm, and different marketing suggestions were given. The experimental …analysis proves the usability of the ILSO-K-means algorithm in customer segmentation, which can be further applied in practice. Show more

Keywords: Clustering algorithm, marketing, customer segmentation, lion cluster optimization algorithm, marketing methods

DOI: 10.3233/JIFS-232589

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5441-5448, 2023

Authors: Huang, Kai | Wang, Jian

Article Type: Research Article

Abstract: Demand forecasting of auto parts is an essential part of inventory control in the automotive supply chain. Due to non-stationarity, strong randomness, local mutation, and non-linearity in short-term auto parts demand data, and it is difficult to predict accurately. In this regard, this paper proposes a combination prediction model based on EEMD-CNN-BiLSTM-attention. First, the model uses the ensemble empirical mode decomposition method to decompose the original data into a series of eigenmode functions and a residual item to extract more feature information. And then uses the CNN-BiLSTM-attention model to analyze each mode separately. The components are predicted, and the prediction …results are summed to obtain the final prediction result. The attention mechanism is introduced to automatically assign corresponding weights to the BiLSTM hidden layer states to distinguish the importance of different time load sequences, which can effectively reduce the loss of historical information and highlight the input of critical historical time points. Finally, the final auto parts demand prediction results are output through the fully connected layer. Then, we conduct an experimental analysis of the collected short-term demand data for auto parts. Finally, the experimental results show that the prediction model proposed in this paper has more minor errors, higher prediction accuracy, and the model prediction performance is better than the other nine comparison models, thus verifying the EEMD-CNN-BiLSTM-attention model for short-term parts demand forecasting effectiveness. Show more

Keywords: Demand forecasting, EEMD, BiLSTM, short-term demand, auto parts

DOI: 10.3233/JIFS-224222

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5449-5465, 2023

Authors: Sivakami, K. | Vijayalakshmi, P.

Article Type: Research Article

Abstract: WSNs(Wireless Sensor Networks) has been developed with applications in many domains including agriculture, telecommunication, manufacturing industry, healthcare, and surveillance. More specifically, WSN plays a pivotal role in IoT (Internet of Things). The IoT sensors provide information about the physical phenomena in the deployed fields. As the sensors contain only limited resources, the factors like data processing, power consumption, transmission, and storage capabilities adversely affect the efficiency. Thus, the process of routing is necessary for network longevity. The data from IoT-based sensors is routed to the destination through a multi-hop routing system. The Energy aware Routing is motivated by the nature …inspired Fuzzy Butterfly Optimization (E2RFBOA). Further a new data aggregation method is introduced in this article customized for IoT based WSN to acquaint higher crop yield in precision farming. Nevertheless, the scalability becomes a primary concern when deployed in larger and denser networks. This is due to the fact that all nodes in IoT and WSN are mostly alive depending on higher usage of bandwidth and power. The primal aim is to build a novel routing protocol developed for IoT-WSN. Apart from this, an Energy aware Clustered Routing that is motivated by Adaptive Elephant Herding Optimization (E2CR-AEHO) is proposed, which sensors collect data and find a group of Cluster Heads (CHs). In the AEHO Algorithm, the formed CH is rotated depending on power consumption. This also prevents frequent re-clustering; at the same time it can effectively adapt to the changes in network topology. According to the AEHOA, the node population comprises of nodes that can choose its CHs among the other nodes. This algorithm takes into account a number of criteria, including power consumption, residual power of Sensor Nodes (SN), network reliability, and data reliability. The suggested approach can efficiently represent the network environment, allowing the routing algorithm to avoid passing over marked zones. Network-specific performances measures including PDRs (Packet Delivery Ratios), NLs (Network Lifetimes), PLRs (Packet Loss Ratios), and AE2E (Average End To End) delay are used to evaluate simulation outcomes. This proposed framework aggregates IoT, which can gradually reduce the amount of data, hence extending network lifetime. Show more

Keywords: Internet of things, swarm intelligence, information fusion, integer linear programming, adaptive elephant herding optimization, wireless sensor networks

DOI: 10.3233/JIFS-224251

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5467-5479, 2023

Authors: Luo, Jiangnan | Cai, Jinyu | Li, Jianping | Gao, Jiuhua | Zhou, Feng | Chen, Kailang | Liu, Lei | Hao, Mengda

Article Type: Research Article

Abstract: This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433 .

DOI: 10.3233/JIFS-232162

Citation: Journal of Intelligent & Fuzzy Systems, vol. 45, no. 4, pp. 5481-5492, 2023