Journal of Intelligent & Fuzzy Systems - Volume 44, issue 1

Authors: Kumar, Arvind | Singh Sodhi, Sartaj

Article Type: Research Article

Abstract: A Neural Network is one of the techniques by which we classify data. In this paper, we have proposed an effectively stacked autoencoder with the help of a modified sigmoid activation function. We have made a two-layer stacked autoencoder with a modified sigmoid activation function. We have compared our autoencoder to the existing autoencoder technique. In the existing autoencoder technique, we generally use the logsigmoid activation function. But in multiple cases using this technique, we cannot achieve better results. In that case, we may use our technique for achieving better results. Our proposed autoencoder may achieve better results compared to …this existing autoencoder technique. The reason behind this is that our modified sigmoid activation function gives more variations for different input values. We have tested our proposed autoencoder on the iris, glass, wine, ovarian, and digit image datasets for comparison propose. The existing autoencoder technique has achieved 96% accuracy on the iris, 91% accuracy on wine, 95.4% accuracy on ovarian, 96.3% accuracy on glass, and 98.7% accuracy on digit (image) dataset. Our proposed autoencoder has achieved 100% accuracy on the iris, wine, ovarian, and glass, and 99.4% accuracy on digit (image) datasets. For more verification of the effeteness of our proposed autoencoder, we have taken three more datasets. They are abalone, thyroid, and chemical datasets. Our proposed autoencoder has achieved 100% accuracy on the abalone and chemical, and 96% accuracy on thyroid datasets. Show more

Keywords: Autoencoder, sigmoid activation function, logsigmoid, neural network, classification, stacked autoencoder

DOI: 10.3233/JIFS-212873

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 1-18, 2023

Authors: Abbasi, Hamid | Yaghoobi, Mahdi | Sharifi, Arash | Teshnehlab, Mohammad

Article Type: Research Article

Abstract: This paper presents an innovative architecture called cascade chaotic fuzzy system (CCFS) for the function approximation and chaotic modeling. The proposed model can dominate complications in the type-2 fuzzy systems and increase the chaotic performance of a whole framework. The proposed cascade structure is based on combining two or more one-dimensional chaotic maps. The combination provides a new chaotic map with more high nonlinearity than its grain maps. The fusion of cascade chaotic structure into the neurons of the membership layer of a conventional fuzzy system makes the CCFS more capable of confronting nonlinear problems. Based on the General Function …Approximation and Stone-Weierstrass theorem, we show that the proposed model has the function approximation property. By analyzing the bifurcation diagram and applying the CCFS to the problem of chaotic modeling, the new model is investigated. Simulation results and analysis are demonstrated to illustrate the concept of general function approximation. Show more

Keywords: Chaotic fuzzy system, function approximation, chaotic neural network, oscillatory neuron

DOI: 10.3233/JIFS-213405

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 19-40, 2023

Authors: Bhatnagar, Manisha | Thankachan, Dolly

Article Type: Research Article

Abstract: Trust enabled wireless networks use temporal behaviour information of nodes in order to classify them into different trust categories. This information is utilized by the router for high performance communication that is optimized in terms of end-to-end delay, energy consumption, throughput, packet delivery ratio, and other quality of service (QoS) parameters. Establishing security in trust enabled wireless networks is a difficult task, because high trust nodes might be compromised by external or internal attacks, thereby disrupting normal communication. In order to perform this task, blockchain based security models are deployed. These models provide high transparency, comprehensive traceability, distributed processing, and …data immutability, which makes them highly deployable for trust enabled networks. Blockchain models enforce compulsive verification of data before communication, which makes them resilient to DDoS, MITM, denial of service, and other data-based attacks. In order to enforce these checks, each of the block is hashed, and the hash values are compared with every existing block in the chain. These checks include hash uniqueness, and hash pattern validations; the later of which is decided by the network designer(s). As the length of blockchain increases, computational complexity of adding a new block (a.k.a. blockchain mining) increases exponentially, which adds to the end-to-end delay, and energy consumption of wireless nodes, which is a drawback of these models. To avoid this, sidechains & blockchain sharding models are developed. These models work by dividing the existing blockchain into multiple parts (based on a certain pre-set criteria), and then use the parts for high speed and low power mining. But again, due to increase in number of sidechains, the computational complexity of managing these chains, and locating data blocks within them increases exponentially. Moreover, in any practical wireless network, there is a need to communicate modifiable data, which is not supported by current blockchain implementations. In order to resolve these issues, this text proposes a transformable blockchain sharding model, which is managed via a light weight meta heuristic method for high-speed data access. The proposed model aims at reducing computational complexity of sidechain maintenance with the help of directed acyclic graphs (DAGs) for storing of hash ranges. The model also incorporates a transformable blockchain solution, wherein the block structure is designed to incorporate selectively mutable as well as non-mutable information. Both the mutable and non-mutable information is encrypted using high performance elliptic curve cryptosystem, which makes it highly secure against network attacks. The proposed model showcases 15% improvement in network lifetime, 8% reduction in end-to-end delay, 22% reduction in computational complexity, and 18% improvement in network throughput when compared with various blockchain and sidechain based wireless networks, thereby assisting in development of a high QoS and highly secure wireless network. Show more

Keywords: Wireless, trust-enabled, sharding, blockchain, meta heuristic, DAG

DOI: 10.3233/JIFS-213482

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 41-58, 2023

Authors: Priyanka, S. | Shanthi, S.

Article Type: Research Article

Abstract: Drowsiness is the inactivated state of the brain and observed during the transition from awaken state to sleepy state. This inactive state diminishes an individual’s attention and leads to accidents during professional or personal activities. The prediction of this inactive (drowsiness) state using AI plays a substantial role in the avoidance of accidents. The advancements in the field of Artificial Intelligence and Neuroscience approaches are used for the prediction of this inactive drowsy state. In order to prevent these devastating accidents, the state of drowsiness of the driver has to be be monitored. Electroencephalogram (EEG) is a predominant tool adopted …to examine various states of the brain effectually. It is generally known as Brain-Computer Interface System. The EEG channels are used for predicting the inactive state while implementing the real-time applications. However, the researchers face various challenges during execution based on the classification and channel selection process. This research concentrates on modelling and efficient drowsiness prediction methods and intends to bridge the gap encountered in the existing approaches. A novel stacked Long Short-Term Memory(s  - LSTM ) with Deep Fully Connected- Convolutional Neural Network (DFC  - CNN ) is used to learn and memorize the long-term feature dependencies and attains essential information based on time-series prediction. Single and multi-channel EEG data is considered to measure the statistical characteristics of available EEG signals. The online available OpenBCI sleep analysis data is used for performing the experimentation, and run in GoogleColab environment. The proposed s  - LSTM model provides a better trade-off compared to existing approaches. The model generalization is improved with the validation of combined feature subjects. Here, metrics like prediction accuracy, RMSE, false positives, scaling coefficients related to false positives are measured to show the significance of the model. Show more

Keywords: Drowsiness, deep learning, stacked long-short term memory, accident risk, statistical measure, generalization

DOI: 10.3233/JIFS-220024

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 59-73, 2023

Authors: Tan, Guxia

Article Type: Research Article

Abstract: A heart attack is a common cause of death globally. It can be treated successfully through a simple and accurate diagnosis. Getting the right diagnosis at the right time is very important for the treatment of heart failure. Currently, the conventional method of diagnosing heart disease is not reliable. Machine learning is a type of artificial intelligence that can be used to analyze the data collected by sensors. Data mining is another type of technology that can be utilized in the healthcare industry. These techniques help predict heart disease based on various factors. We developed a prediction and recommendation model …aimed at predicting heart disease using the Optimized Deep Belief Network. It does so by taking into account the various features of the heart disease UCI and Stalog database. Finally, the proposed method classifies healthy people and people with heart illness with an accuracy of 97.91%. Show more

Keywords: MSVDIS, MV-data, FR-set, FRIC-model, Evaluation function, A-reduction

DOI: 10.3233/JIFS-220225

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 75-90, 2023

Authors: Perumal, Balamurugan | Ganeshan, Arulkumaran | Jayagopalan, Santhosh | Preetha, K.S. | Selamban, Ramasamy | Elangovan, Dinesh | Balasubramani, Sumathy

Article Type: Research Article

Abstract: The problem of smart agriculture has been well studied and the security in Wireless Sensor Networks (WSN) has been analyzed in detail. There are a number of approaches discussed in the literature to support the growth of agriculture by considering different factors. But still the performance of plant management is not up to the expected level in terms of plant management and security concern. To handle these issues, an efficient multi view image based plant management technique which consider color and contrast features to obtain the features of fluid, plant, climate to compute different supportive measures like Fluid Specific Growth …Support (FSGS), Plant Specific Growth Support (PSGS) and Climate Specific Growth Support (CSGS) measures to compute the value of Plant Growth Measure (PGM) and Crop Yield Measure (CYM). Also, using the same support measures, the presence of diseased plants is identified and fertilizers are regulated accordingly. Similarly, the wireless sensor network has been used as monitoring environment which has several routes to monitor different locations of agriculture lands. The presences of different routes are monitored for the transmission of different agriculture data. To handle the security issues, a low rate attack detection scheme is presented which finds the routes and for each route the method computes Service centric Legitimate Support (SCLS) to find low rate attacks. Similarly, the data security by controlling different smart devices in agriculture lands is enforced by using service centric data encryption (SCDE) scheme which uses different encryption scheme and keys to encrypt the data being used for controlling the devices of agricultural lands. The proposed method improves the performance of smart agriculture and improves the data security with higher low rate detection accuracy. Show more

Keywords: WSN, smart agriculture, data security, low rate attack, plant management, crop yield

DOI: 10.3233/JIFS-220594

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 91-100, 2023

Authors: Chen, Peng | Zhu, Dongge

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-220675

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 101-112, 2023

Authors: Masood, Faraz | Faridi, Arman Rasool

Article Type: Research Article

Abstract: Blockchain technology is getting famous, and use cases of blockchain range from financial services to the Metaverse. It is considered a platform for web 3.0. As a result, many industries are planning to adopt blockchain. A simple public blockchain is not suitable for most business scenarios, so hybrid and private blockchains came into existence, but it is important to decide which type of blockchain should be adopted during the project planning phase. Various models can be found in the literature to determine if blockchain should be adopted and, if so, which type of blockchain should be adopted. However, these models …are already becoming obsolete as they determine the usage of blockchain using simple yes or no. In order to overcome these problems, all these models are converted from binary-based selection to fuzzy-based selection, and decision matrices are created. Various multi-criteria decision analysis methods are applied, and final results are obtained. In addition, a novel model is presented, and a MATLAB application is developed to let the user determine if blockchain can be integrated with any technology or not. This application can be used as a standard in the project’s planning phase and helps avoid losses to the industry. Show more

Keywords: Blockchain, decision making, distributed ledger, SAW, TOPSIS

DOI: 10.3233/JIFS-220830

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 113-124, 2023

Authors: Sundaramurthy, Shanmugam | Sugumaran, Vijayan | Thangavelu, Arunkumar | Sekaran, Karthik

Article Type: Research Article

Abstract: Rheumatoid Arthritis (RA) is a chronic autoimmune disease whose symptoms are hard to determine due to the overlapping indications of the condition with other illnesses such as dengue, malaria, etc. As the symptoms of RA disease are similar to inflammatory diseases, general physicians (GPs) find it difficult to detect the disease earlier. A computer aided framework is proposed in this study to assist and support the GPs to diagnose RA better. In this work Improved Harmony Search Optimization (IHSO) approach is proposed to select the significant feature subset of RA and Adaptive Neuro-Fuzzy Inference System (ANFIS) is used as a …classification model. The performance of the proposed IHSO-ANFIS model is examined with metrics such as Balanced Accuracy (Bacc), Area under Curve (AUC), Sensitivity (Sen), Specificity (Spec), and Matthew’s Correlation Coefficient (MCC) using 10-Fold cross-validation. Additionally, the results of the IHSO-ANFIS are compared with HSO-ANFIS, ANFIS without any feature selection and standard bench mark datasets. IHSO-ANFIS attained 87.05% Bacc, 89.95% AUC and 0.6586 MCC on the RA dataset. From the results it is clear that IHSO-ANFIS could assist general physicians to diagnose RA earlier and pave the way for timely treatment. Show more

Keywords: Rheumatoid arthritis, hybrid harmony search, particle swarm optimization, disease diagnosis, ANFIS

DOI: 10.3233/JIFS-221252

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 125-137, 2023

Authors: Suresh, M. | Venkata Satya Vivek, Tammineedi | Venkat, Yalla | Chokkalingam, Mohan

Article Type: Research Article

Abstract: The lack of awareness of blind spots in vehicle transport results in more deaths nowadays. To address this issue, the multi-obstacle detection and measurement of the depth of the nearing vehicle, height, and width is necessary. In recent years, Fuzzy logic is being used to access smart decision-making for control actions. To handle the specific task efficiently, ambiguous and imprecise linguistic data is required. In this context, a non-linear intelligent fuzzy decision-making system has been proposed to estimate blind spots. An inference engine, a defuzzification interface to identify the blind spot both day and night, and a fuzzy rule-base are …included. Shadows and edges can be used as linguistic parameters to identify vehicles in the daytime. The lamps are elevated higher than the air dams to avoid casting a shadow under the car at night. One in-sourcing vehicle and three out-sourcing vehicles are tested to determine the driver’s blind spot and a more comfortable driver’s seat and a rear-view mirror using the proposed system. A fuzzy matrix with a triangular number obtained from the crisp matrix is used to alert the driver of the likelihood of a collision using LEDs or buzzers. Show more

Keywords: Non-linearity, Fuzzy decision-making system, blind spot estimation, vehicle detection system

DOI: 10.3233/JIFS-213426

Citation: Journal of Intelligent & Fuzzy Systems, vol. 44, no. 1, pp. 139-148, 2023