Adaptive habitat biogeography-based optimizer for optimizing deep CNN hyperparameters in image classification.

Deep Convolutional Neural Networks (DCNNs) have shown remarkable success in image classification tasks, but optimizing their hyperparameters can be challenging due to their complex structure. This paper develops the Adaptive Habitat Biogeography-Based Optimizer (AHBBO) for tuning the hyperparameters of DCNNs in image classification tasks. In complicated optimization problems, the BBO suffers from premature convergence and insufficient exploration. In this regard, an adaptable habitat is presented as a solution to these problems; it would permit variable habitat sizes and regulated mutation. Better optimization performance and a greater chance of finding high-quality solutions across a wide range of problem domains are the results of this modification's increased exploration and population diversity. AHBBO is tested on 53 benchmark optimization functions and demonstrates its effectiveness in improving initial stochastic solutions and converging faster to the optimum. Furthermore, DCNN-AHBBO is compared to 23 well-known image classifiers on nine challenging image classification problems and shows superior performance in reducing the error rate by up to 5.14%. Our proposed algorithm outperforms 13 benchmark classifiers in 87 out of 95 evaluations, providing a high-performance and reliable solution for optimizing DNNs in image classification tasks. This research contributes to the field of deep learning by proposing a new optimization algorithm that can improve the efficiency of deep neural networks in image classification.

FUZ-SMO: A fuzzy slime mould optimizer for mitigating false alarm rates in the classification of underwater datasets using deep convolutional neural networks.

Sonar sound datasets are of significant importance in the domains of underwater surveillance and marine research as they enable experts to discern intricate patterns within the depths of the water. Nevertheless, the task of classifying sonar sound datasets continues to pose significant challenges. In this study, we present a novel approach aimed at enhancing the precision and efficacy of sonar sound dataset classification. The integration of deep long-short-term memory (DLSTM) and convolutional neural networks (CNNs) models is employed in order to capitalize on their respective advantages while also utilizing distinctive feature engineering techniques to achieve the most favorable outcomes. Although DLSTM networks have demonstrated effectiveness in tasks involving sequence classification, attaining their optimal performance necessitates careful adjustment of hyperparameters. While traditional methods such as grid and random search are effective, they frequently encounter challenges related to computational inefficiencies. This study aims to investigate the unexplored capabilities of the fuzzy slime mould optimizer (FUZ-SMO) in the context of LSTM hyperparameter tuning, with the objective of addressing the existing research gap in this area. Drawing inspiration from the adaptive behavior exhibited by slime moulds, the FUZ-SMO proposes a novel approach to optimization. The amalgamated model, which combines CNN, LSTM, fuzzy, and SMO, exhibits a notable improvement in classification accuracy, outperforming conventional LSTM architectures by a margin of 2.142%. This model not only demonstrates accelerated convergence milestones but also displays significant resilience against overfitting tendencies.

Machine learning in action: Revolutionizing intracranial hematoma detection and patient transport decision-making.

Objectives: Traumatic intracranial hematomas represent a critical clinical situation where early detection and management are of utmost importance. Machine learning has been recently used in the detection of neuroradiological findings. Hence, it can be used in the detection of intracranial hematomas and furtherly initiate a management cascade of patient transfer, diagnostics, admission, and emergency intervention. We aim, here, to develop a diagnostic tool based on artificial intelligence to detect hematomas instantaneously, and automatically start a cascade of actions that support the management protocol depending on the early diagnosis. Materials and Methods: A plot was designed as a staged model: The first stage of initiating and training the machine with the provisional evaluation of its accuracy and the second stage of supervised use in a tertiary care hospital and a third stage of its generalization in primary and secondary care hospitals. Two datasets were used: CQ500, a public dataset, and our dataset collected retrospectively from our tertiary hospital. Results: A mean dice score of 0.83 was achieved on the validation set of CQ500. Moreover, the detection of intracranial hemorrhage was successful in 94% of cases for the CQ500 test set and 93% for our local institute cases. Poor detection was present in only 6-7% of the total test set. Moderate false-positive results were encountered in 18% and major false positives reached 5% for the total test set. Conclusion: The proposed approach for the early detection of acute intracranial hematomas provides a reliable outset for generating an automatically initiated management cascade in high-flow hospitals.

Oncological Clearance Following Resection of the Carcinoma Rectum: A Comparison between Laparoscopic and Open Anterior Resection.

Till the day the rectal cancer deaths in the world is in eighth position. For rectal cancer surgery, short-term benefits are expected to be similar for laparoscopic resection of rectum (LRR) and open resection of rectum (ORR). In Bangladesh though the rectal cancer is the sixteenth most common cause of cancer deaths, there is lack of data regarding outcomes of laparoscopic and open surgical approaches for carcinoma rectum. Purpose of study was to compare oncopathological outcomes by quality of surgical resection between LRR and ORR groups. The quasi experimental study was conducted among 46 subjects who attended in the Department of Colorectal Surgery, Bangabandhu Sheikh Mujib Medical University, Bangladesh from July 2020 to June 2021 with rectal adenocarcinoma within 15cm from the anal verge. Equal number of subjects were allocated for LRR and ORR group. Oncopathological end points such as circumferential resection margin (CRM), distal resection margin (DRM), lymph nodes and quality of mesorectal excision were assessed and compared. Here every patients have given their written consent for this study. Mean age of the subjects for LRR and ORR were 45.47±12.66 and 44.47±12.48 years respectively. Majority of the subjects were in age above 40 years (67.0%). The proportion of male (56.5%) were higher than those of female (43.5%). The complete resection was better in LRR (91.3%) than ORR (87.0%) group though statistically not significant. CRM was lower in LRR (0.0%) than ORR (13.0%) group in respect of frequency distribution. DRM was negative for both LRR and ORR group (95.7% each) and it was not statistically significant. ORR met the National Comprehensive Cancer Network (NCCN) criteria of harvesting 12 lymph nodes were as in LRR group 10 lymph nodes were harvested. The mean harvested lymph nodes were 12.2±5.55 and 10.1±5.55 in LRR and ORR group respectively. The study demonstrated that LRR is better (though statistically not significant) in respect of complete resection and CRM while in harvesting lymph nodes, ORR met the NCCN criteria but LRR does not. There is no difference observed regarding DRM in both groups. On oncopathological point of view both the group showed almost equally effective results. Laparoscopic surgery can be opted as the standard operative technique for surgical management of rectal cancer.

Self-assembling Organogels Loaded with Tenoxicam for Local Intensive Pain and Inflammation Cure: In Vitro and In Vivo Correlation.

Due to tenoxicam (TX)'s poor aqueous solubility (0.072 mg/ml), it is poorly absorbable in the GIT, and the long-term oral administration of TX may cause severe GIT disturbances. Topical administration of TX can help in bypassing the GIT adverse effects. Therefore, in the present work, we constructed different pluronic/lecithin organogels (PLOs) for topical delivery of TX. PLO was constructed simply via direct mixing of an aqueous pluronic solution with lecithin solution. The prepared PLO formulations were characterized for their physicochemical properties including pH, drug content, visual inspection, viscosity, and spreadability. Also, the in vitro release and kinetic studies were carried out to investigate the mechanism of drug release. Moreover, the in vivo studies were carried out by investigating the anti-inflammatory and analgesic activities using albino male rats. The results showed that the modified PLOs have good physicochemical properties. The viscosity of the modified gels is a direct proportionality with both lecithin and pluronic concentrations. Also, subsequently, the drug release rate is directly proportional to gel viscosity. Moreover, the in vivo studies showed that the modified PLOs (F19) showed a significant ( < 0.05%) paw edema inhibition and pain analgesia compared with other investigated groups. Also, the results indicated that the increase in dose is accompanied by higher activity and a longer duration of action which extended to 12 h. Hence, the modified PLOs are promising safe candidates or vehicles for effective TX loading with sustained delivery behavior.

Sustainable utilization of the vegetable oil manufacturing waste product in the formulation of eco-friendly emulsifiable cutting fluids.

The conventional Metal cutting fluids (MCFs) used are mineral-based petroleum oils that perform well but are toxic and difficult to dispose of; therefore, these are hazardous to human health as well as the environment. This issue can be solved by using natural vegetable oil-based MCF, which are readily available, environment and human-friendly, and renewable. Therefore, we synthesized various types of emulsifiers (anionic, and nonionic with different ethylene oxide units as well as mono and gemini cationic surfactants as corrosion inhibitors and biocides) based on recycled vegetable oil (RO) from spent bleaching earth (SBE), and elucidated their chemical structures by different spectroscopic techniques. The individually synthesized emulsifiers (anionic, and nonionic with different ethylene oxide units) at different ratios (8-15 by wt.%) and mixed emulsifiers (anionic/nonionic, nonionic/nonionic with different degrees of ethylene oxide) at different ratios (8-12 by wt.%) were utilized as additives in the preparation of different vegetable residual oil-based MCF formulations. The mixed emulsifiers at different ratios of nonionic/nonionic with hydrophilic-lipophilic balance (HLB) value 10 (Formulas I, II, III, and IV), and anionic/nonionic (Formula V, and VI) exhibited stable emulsions compared to individual emulsifiers. Formulas (I and VI) displayed good protection effectiveness in corrosion tests. Formula VI had better wettability (25.22 on CS, 23.68 on Al, and 22.28 on WC) and a smaller particle size (63.97 nm). Tribological properties of Formula VI were also performed. The results exhibit that Formula VI is consistent with the commercial sample. As a result, this study contributed to the resolution of one of the industry's problems.

Dalbergiella welwitschia (Baker) Baker f. alkaloid-rich extracts attenuate liver damage in streptozotocin-induced diabetic rats.

This experiment was conducted to evaluate the Dalbergiella welwitschia alkaloid-rich extracts on liver damage in streptozotocin-induced diabetic rats. Hence, to induce diabetes, 45 mg/kg body weight of streptozotocin was intraperitoneally injected into the Wistar rats. Subsequently, 5 % (w/v) of glucose water was given to the induced animals for 24 h. Thus, the animals (48) were grouped into five groups (n = 8), containing normal control (NC), diabetic control (DC), diabetic rats placed on low (50 mg/kg body weight) and high (100 mg/kg body weight) doses of D. welwitschi alkaloid-rich leaf extracts (i.e. DWL and DWH respectively), and diabetic rats administered 200 mg/kg body weight of metformin (MET). The animals were sacrificed on the 21st day of the experiment, blood and liver were harvested, and different liver damage biomarkers were evaluated. The results obtained demonstrated that diabetic rats administered DWL, DWH and MET significantly (p < 0.05) increased hepatic AST, ALT, albumin, SOD, CAT, GSH, and GPX levels when compared to DC with no significant (p > 0.05) different when compared with NC. Also, diabetic rats administered DWL, DWH and MET revealed a significant (p < 0.05) decrease in GGT and MDA levels, as well as, fragmented DNA and protein carbonyl levels when compared to DC with no significant (p > 0.05) different when compared with NC. In addition, histological examination revealed that diabetic rats placed on DWL, DWH and MET normalized the hepatocytes. Consequently, it can be inferred that alkaloid-rich extracts from D. welwitschi leaf could be helpful in improving liver damage associated with diabetes mellitus rats.

Optimized Visual Internet of Things for Video Streaming Enhancement in 5G Sensor Network Devices.

The global expansion of the Visual Internet of Things (VIoT)'s deployment with multiple devices and sensor interconnections has been widespread. Frame collusion and buffering delays are the primary artifacts in the broad area of VIoT networking applications due to significant packet loss and network congestion. Numerous studies have been carried out on the impact of packet loss on Quality of Experience (QoE) for a wide range of applications. In this paper, a lossy video transmission framework for the VIoT considering the KNN classifier merged with the H.265 protocols. The performance of the proposed framework was assessed while considering the congestion of encrypted static images transmitted to the wireless sensor networks. The performance analysis of the proposed KNN-H.265 protocol is compared with the existing traditional H.265 and H.264 protocols. The analysis suggests that the traditional H.264 and H.265 protocols cause video conversation packet drops. The performance of the proposed protocol is estimated with the parameters of frame number, delay, throughput, packet loss ratio, and Peak Signal to Noise Ratio (PSNR) on MATLAB 2018a simulation software. The proposed model gives 4% and 6% better PSNR values than the existing two methods and better throughput.

The effect of different kinematics on apical debris extrusion with a single-file system.

To compare the amount of extruded debris caused by different motions using a single-file system. Fifty mandibular first molar teeth were randomized into 5 groups (n = 10) according to the motion tested: Optimize Torque Reverse (OTR), TF Adaptive Motion (TFA), continuous rotation (CR), reciprocation motion (+ 150°, -30°) (REC), and Jeni motion (Jeni). One Curve single file 25/06 (Micro-Mega, Besançon, France) was used in all experimental groups. The root canals were irrigated with 2.5% NaOCl, and the extruded debris were collected at pre-weighted glass vials. The glass vials were kept inside an incubator for one week at 70 °C to dry out the irrigating solution. The extruded debris was quantified by subtracting the pre-instrumentation from the post-instrumentation weight of the glass vials. The time required for each instrumentation procedure was digitally recorded. All data were analyzed statistically with one way ANOVA and post hoc Tukey test (P < 0.05). All the motions extruded apically debris with Jeni mode caused significantly less debris extrusion than TFA, REC, and CR (P < 0.05) while no significant difference emerged with OTR. Preparation time was not significantly different in all groups. Within the limits of the present study, all the kinematics produced apically debris extrusion, with Jeni reporting a similar amount of debris compared with OTR and significantly less than TFA, REC, and CR. Preparation time was similar among the tested kinematics.

Risk factors of congenital hydrocephalus: a case-control study in a lower-middle-income country (Egypt).

OBJECTIVE: Hydrocephalus is the most common brain disorder in children and is more common in low- and middle-income countries. Research output on hydrocephalus remains sparse and of lower quality in low- and middle-income countries compared with high-income countries. Most studies addressing hydrocephalus epidemiology are retrospective registry studies entailing their inherent limitations and biases. This study aimed to investigate child-related, parental, and socioeconomic risk factors of congenital hydrocephalus (CH) in a lower-middle-income country. METHODS: An investigator-administered questionnaire was used to query parents of patients with CH and controls who visited the authors' institution from 2017 until 2021. Patients with secondary hydrocephalus and children older than 2 years of age at diagnosis were excluded. Uni- and multivariable logistic regression was performed to identify the factors affecting CH development. RESULTS: Seven hundred forty-one respondents (312 cases and 429 controls) were included in this study. The authors showed that maternal diseases during pregnancy (OR 3.12, 95% CI 1.96-5.03), a lack of periconceptional folic acid intake (OR 1.92, 95% CI 1.32-2.81), being a housewife (OR 2.66, 95% CI 1.51-4.87), paternal illiteracy (OR 1.65, 95% CI 1.02-2.69), parental consanguinity (OR 3.67, 95% CI 2.40-5.69), a history of other CNS conditions in the family (OR 2.93, 95% CI 1.24-7.34), conceiving a child via assisted fertilization techniques (OR 3.93, 95% CI 1.57-10.52), and the presence of other congenital anomalies (OR 2.57, 95% CI 1.38-4.87) were associated with an independent higher odds of a child having CH. Conversely, maternal hypertension (OR 0.22, 95% CI 0.09-0.48), older maternal age at delivery (OR 0.93, 95% CI 0.89-0.97), and having more abortions (OR 0.80, 95% CI 0.67-0.95) were negatively correlated with CH. CONCLUSIONS: Multiple parental, socioeconomic, and child-related factors were associated with higher odds for developing CH. These results can be utilized to guide parental counseling and management, and direct social education and prevention programs.

European Association for Endoscopic Surgery (EAES) consensus on Indocyanine Green (ICG) fluorescence-guided surgery.

BACKGROUND: In recent years, the use of Indocyanine Green (ICG) fluorescence-guided surgery during open and laparoscopic procedures has exponentially expanded across various clinical settings. The European Association of Endoscopic Surgery (EAES) initiated a consensus development conference on this topic with the aim of creating evidence-based statements and recommendations for the surgical community. METHODS: An expert panel of surgeons has been selected and invited to participate to this project. Systematic reviews of the PubMed, Embase and Cochrane libraries were performed to identify evidence on potential benefits of ICG fluorescence-guided surgery on clinical practice and patient outcomes. Statements and recommendations were prepared and unanimously agreed by the panel; they were then submitted to all EAES members through a two-rounds online survey and results presented at the EAES annual congress, Barcelona, November 2021. RESULTS: A total of 18,273 abstracts were screened with 117 articles included. 22 statements and 16 recommendations were generated and approved. In some areas, such as the use of ICG fluorescence-guided surgery during laparoscopic cholecystectomy, the perfusion assessment in colorectal surgery and the search for the sentinel lymph nodes in gynaecological malignancies, the large number of evidences in literature has allowed us to strongly recommend the use of ICG for a better anatomical definition and a reduction in post-operative complications. CONCLUSIONS: Overall, from the systematic literature review performed by the experts panel and the survey extended to all EAES members, ICG fluorescence-guided surgery could be considered a safe and effective technology. Future robust clinical research is required to specifically validate multiple organ-specific applications and the potential benefits of this technique on clinical outcomes.

A Novel Approach for the Availability and Ocular Delivery of Tenoxicam Potassium: Synthesis, Characterization, and In Vivo Application.

Tenoxicam (TX) is a non-steroidal anti-inflammatory agent that can be used to control pain in various ophthalmic lesions like cataracts, refractive surgery, and corneal abrasion. TX has a very slightly aqueous solubility of 0.072 mg/mL resulting in difficulty to be formulated in ophthalmic solutions. This study aims to improve TX solubility by converting it into its potassium salt to achieve a target of 10 mg/mL (1%w/v) concentration of TX in the desired aqueous medium for the formulation of aqueous ophthalmic solutions. The synthesized TX salt was characterized by different evaluation parameters such as solubility studies, 1H NMR, IR, and elemental analyses. Different TX potassium solutions were formulated at concentrations of 0.5% and 1% w/v using different viscosity-imparting agents. The prepared solutions were characterized for their physicochemical properties including visual inspection, pH, rheological, in vitro release, and kinetic behavior. Also, the formulations were biologically evaluated in vivo using male albino rabbits. The obtained results showed the successful synthesis of TX salt, as indicated by IR and NMR, and elemental analysis. The solubility study showed that the solubility of TX was improved hugely to 18 mg/mL (250-fold). In addition, the results showed that the prepared formulations showed acceptable physicochemical properties. The highest release rate was obtained with formula F1, which contains no viscosity-imparting agents. While as, the lowest release rate was obtained in the case of formula F9, composed of Pluronic F127 (12% w/v). The in vivo results showed that TX optimized ophthalmic solutions F8 and F9 inhibited the redness and edema in an extended or sustained manner.

Kidney Cancer Prediction Empowered with Blockchain Security Using Transfer Learning.

Kidney cancer is a very dangerous and lethal cancerous disease caused by kidney tumors or by genetic renal disease, and very few patients survive because there is no method for early prediction of kidney cancer. Early prediction of kidney cancer helps doctors start proper therapy and treatment for the patients, preventing kidney tumors and renal transplantation. With the adaptation of artificial intelligence, automated tools empowered with different deep learning and machine learning algorithms can predict cancers. In this study, the proposed model used the Internet of Medical Things (IoMT)-based transfer learning technique with different deep learning algorithms to predict kidney cancer in its early stages, and for the patient's data security, the proposed model incorporates blockchain technology-based private clouds and transfer-learning trained models. To predict kidney cancer, the proposed model used biopsies of cancerous kidneys consisting of three classes. The proposed model achieved the highest training accuracy and prediction accuracy of 99.8% and 99.20%, respectively, empowered with data augmentation and without augmentation, and the proposed model achieved 93.75% prediction accuracy during validation. Transfer learning provides a promising framework with the combination of IoMT technologies and blockchain technology layers to enhance the diagnosing capabilities of kidney cancer.

Clinical Outcome of 0.2% Glyceryl Trinitrate Topical Ointment Compared to Lateral Internal Sphincterotomy in the Treatment of Patient with Chronic Anal Fissure: A Randomized Control Trial.

The objective of study was to evaluate the clinical outcome of topical 0.2% Glyceryl trinitrate topical (GTN) ointment in the treatment of chronic anal fissure. This randomized control trial was carried out in the Colorectal Surgery Unit, Department of Surgery, Bangabandhu Sheikh Mujib Medical University (BSMMU), Bangladesh from May 2015 to April 2016. Total 94 patients were included in this trial, where 47(50.0%) patients were treated by 0.2% GTN ointment as Trial group 12 hourly for 8 weeks and 47(50.0%) patients by lateral internal sphincterotomy (LIS) as Control group in this study. Patients were randomized in two groups by lottery following purposive sampling. Post-procedural outcome variables with 6 months follow up were evaluated. Majority of the patients were found in between 20 to 40 years of age in both groups. The mean age was 34.6±10.4 years and 33.2±8.6 years in GTN and LIS respectively. Overall male female ratio was 0.88:1. All (100.0%) patients presented with pain in anus and 86.15% patients presented with per rectal bleeding. Pain relief in GTN arm versus LIS arm in 2nd and 6th week was 55.31% vs. 76.6%, 74.5% vs. 87.23% with no significant difference between two groups. But at 6 month it was 57.44% vs. 93.6% respectively. The fall in pain relief at 6th month in GTN arm was due to recurrence of fissure. At the end of 2nd, 6th week and 6month, cessation of bleeding improved gradually in both groups after treatment but the improvement was significantly better in LIS group than in GTN group indicating sphincterotomy stops bleeding better. Healing after 2nd week in both groups was minimum but equal 2(4.26%) patients. After 6 weeks LIS group had significant better healing than GTN 40(85.1%) versus 26(55.3%) with p value <0.001. In 6 month time GTN group had increased healing but LIS group had significant better healing than GTN group 42(89.36) vs. 32(68.08) with p value 0.004. Transient flatus and liquid incontinence were 8.51% and 6.4% respectively in LIS group with 0.0% in GTN group. Headache and recurrence were significantly higher in GTN group 61.7% and 34.04% with p<0.001. Lateral internal anal sphincterotomy is superior to the topical application of 0.2% nitroglycerin ointment in the treatment of chronic anal fissure with the advantages of good symptomatic relief, high rate of healing and a very low rate of transient continence disturbances.

A secure healthcare 5.0 system based on blockchain technology entangled with federated learning technique.

In recent years, the global Internet of Medical Things (IoMT) industry has evolved at a tremendous speed. Security and privacy are key concerns on the IoMT, owing to the huge scale and deployment of IoMT networks. Machine learning (ML) and blockchain (BC) technologies have significantly enhanced the capabilities and facilities of healthcare 5.0, spawning a new area known as "Smart Healthcare." By identifying concerns early, a smart healthcare system can help avoid long-term damage. This will enhance the quality of life for patients while reducing their stress and healthcare costs. The IoMT enables a range of functionalities in the field of information technology, one of which is smart and interactive health care. However, combining medical data into a single storage location to train a powerful machine learning model raises concerns about privacy, ownership, and compliance with greater concentration. Federated learning (FL) overcomes the preceding difficulties by utilizing a centralized aggregate server to disseminate a global learning model. Simultaneously, the local participant keeps control of patient information, assuring data confidentiality and security. This article conducts a comprehensive analysis of the findings on blockchain technology entangled with federated learning in healthcare. 5.0. The purpose of this study is to construct a secure health monitoring system in healthcare 5.0 by utilizing a blockchain technology and Intrusion Detection System (IDS) to detect any malicious activity in a healthcare network and enables physicians to monitor patients through medical sensors and take necessary measures periodically by predicting diseases. The proposed system demonstrates that the approach is optimized effectively for healthcare monitoring. In contrast, the proposed healthcare 5.0 system entangled with FL Approach achieves 93.22% accuracy for disease prediction, and the proposed RTS-DELM-based secure healthcare 5.0 system achieves 96.18% accuracy for the estimation of intrusion detection.

AI-Based Prediction of Capital Structure: Performance Comparison of ANN SVM and LR Models.

Capital structure is an integral part of the corporate finance that sources the funds to finance growth and operations. Managers always have to maintain value of the firm to be higher than the cost of capital in order to maximize the shareholders wealth. Empirical studies have used sources of finance like debt and equity as variables of capital structure. A choice between debt and equity finance analyzes the firm's ability to perform under the financially constrained environment to attain the sustainable growth. Therefore, it gives rise to a dire need to estimate the cost of capital precisely. We examined the capital structure of top ten market capitalization of the stock markets included in MSCI Emerging index with the use of artificial neural networks, support vector regression, and linear regression in forecasting methods. The capital structure is measured as the proportion of total debt over total equity (Tang et al., 1991). Other financial ratios such as profitability, liquidity, solvent, and turnover ratios were considered as drivers of the capital structure. Applying logistic and hyperbolic tangent activation functions, it was concluded that ANN has a great potential of replacing other traditional forecasting models with the nonstationary data. This research contributes with a new dimension for estimation through different activation functions. There is a possibility of ANN dominance as compared to the other models applied for predictability in financial markets.

Towards Parallel Selective Attention Using Psychophysiological States as the Basis for Functional Cognition.

Attention is a complex cognitive process with innate resource management and information selection capabilities for maintaining a certain level of functional awareness in socio-cognitive service agents. The human-machine society depends on creating illusionary believable behaviors. These behaviors include processing sensory information based on contextual adaptation and focusing on specific aspects. The cognitive processes based on selective attention help the agent to efficiently utilize its computational resources by scheduling its intellectual tasks, which are not limited to decision-making, goal planning, action selection, and execution of actions. This study reports ongoing work on developing a cognitive architectural framework, a Nature-inspired Humanoid Cognitive Computing Platform for Self-aware and Conscious Agents (NiHA). The NiHA comprises cognitive theories, frameworks, and applications within machine consciousness (MC) and artificial general intelligence (AGI). The paper is focused on top-down and bottom-up attention mechanisms for service agents as a step towards machine consciousness. This study evaluates the behavioral impact of psychophysical states on attention. The proposed agent attains almost 90% accuracy in attention generation. In social interaction, contextual-based working is important, and the agent attains 89% accuracy in its attention by adding and checking the effect of psychophysical states on parallel selective attention. The addition of the emotions to attention process produced more contextual-based responses.

A Novel Grayscale Image Encryption Scheme Based on the Block-Level Swapping of Pixels and the Chaotic System.

Hundreds of image encryption schemes have been conducted (as the literature review indicates). The majority of these schemes use pixels as building blocks for confusion and diffusion operations. Pixel-level operations are time-consuming and, thus, not suitable for many critical applications (e.g., telesurgery). Security is of the utmost importance while writing these schemes. This study aimed to provide a scheme based on block-level scrambling (with increased speed). Three streams of chaotic data were obtained through the intertwining logistic map (ILM). For a given image, the algorithm creates blocks of eight pixels. Two blocks (randomly selected from the long array of blocks) are swapped an arbitrary number of times. Two streams of random numbers facilitate this process. The scrambled image is further XORed with the key image generated through the third stream of random numbers to obtain the final cipher image. Plaintext sensitivity is incorporated through SHA-256 hash codes for the given image. The suggested cipher is subjected to a comprehensive set of security parameters, such as the key space, histogram, correlation coefficient, information entropy, differential attack, peak signal to noise ratio (PSNR), noise, and data loss attack, time complexity, and encryption throughput. In particular, the computational time of 0.1842 s and the throughput of 3.3488 Mbps of this scheme outperforms many published works, which bears immense promise for its real-world application.