Hidden Markov Model for Parkinson's Disease Patients Using Balance Control Data.

Understanding the behavior of the human postural system has become a very attractive topic for many researchers. This system plays a crucial role in maintaining balance during both stationary and moving states. Parkinson's disease (PD) is a prevalent degenerative movement disorder that significantly impacts human stability, leading to falls and injuries. This research introduces an innovative approach that utilizes a hidden Markov model (HMM) to distinguish healthy individuals and those with PD. Interestingly, this methodology employs raw data obtained from stabilometric signals without any preprocessing. The dataset used for this study comprises 60 subjects divided into healthy and PD patients. Impressively, the proposed method achieves an accuracy rate of up to 98% in effectively differentiating healthy subjects from those with PD.

Comparative efficacy of postbiotic, probiotic, and antibiotic against necrotic enteritis in broiler chickens.

Prevention of necrotic enteritis (NE), caused by Clostridium perfringens (C. perfringens), is one of the most important goals to improve the profitability of broiler chickens. This work aimed to compare the efficacy of 2 antibiotic alternatives including a postbiotic (dry feed additive and aqueous nonviable Lactobacillus (L.) species fermentation) and a probiotic (dry feed additive and aqueous Bacillus (B.) subtilis and B. lischeniformis mixture) with an antibiotic (amoxicillin in water) against NE. Four hundred, day-old broiler chicks were divided into 8 equal groups (Gs), n = 50 each (5 replicates; 10 each). Chickens of G1 (postbiotic dry-feed additive), G2 (postbiotic and antibiotic in drinking water), G3 (postbiotic dry and aqueous), G4 (probiotic dry-feed additive), G5 (probiotic and antibiotic in drinking water), G6 (probiotic dry and aqueous), and G7 (nontreated) were orally inoculated with a toxigenic C. perfringens type A on the d 19 to 21 of age and predisposed with 3X coccidial vaccine for induction of NE. However, chickens of G8 were kept nontreated or challenged. The severity of NE signs was markedly decreased in G3 in comparison with other challenged treatment groups, and the mortality rates were 22%, 10%, 16%, 22%, 12%, 20%, and 36% in Gs 1, 2, 3, 4, 5, 6, and 7, respectively. The best significant (P ≤ 0.05) feed conversion ratio was detected in G3 (1.51), G6 (1.54), and G2 and G8 (1.61). In addition, the European production efficiency factor was significantly (P ≤ 0.05) improved in G3 (279.33) and G2 (266.67), but it was decreased in G7 (177.33) when compared with G8 (339.33). An improvement in intestinal and hepatic pathology and liver function tests, as well as a significant (P ≤ 0.05) decrease in bacterial counts were observed in Gs 2, 5, 3, 6, 1, and 4, respectively in comparison with G7. Immunologically, the highest significant (P ≤ 0.05) hemagglutination inhibition antibody titers for Newcastle disease virus vaccine were in Gs 1 and 3 (6.4 log2). In conclusion, the combined feed and water postbiotic treatment demonstrated promising results in ameliorating the severity of NE and improving the hepatic and the immune status of broiler chickens when compared with the commonly used probiotic and antibiotic.

EMD-Based Method for Supervised Classification of Parkinson's Disease Patients Using Balance Control Data.

There has recently been increasing interest in postural stability aimed at gaining a better understanding of the human postural system. This system controls human balance in quiet standing and during locomotion. Parkinson's disease (PD) is the most common degenerative movement disorder that affects human stability and causes falls and injuries. This paper proposes a novel methodology to differentiate between healthy individuals and those with PD through the empirical mode decomposition (EMD) method. EMD enables the breaking down of a complex signal into several elementary signals called intrinsic mode functions (IMFs). Three temporal parameters and three spectral parameters are extracted from each stabilometric signal as well as from its IMFs. Next, the best five features are selected using the feature selection method. The classification task is carried out using four known machine-learning methods, KNN, decision tree, Random Forest and SVM classifiers, over 10-fold cross validation. The used dataset consists of 28 healthy subjects (14 young adults and 14 old adults) and 32 PD patients (12 young adults and 20 old adults). The SVM method has a performance of 92% and the Dempster-Sahfer formalism method has an accuracy of 96.51%.

RAPT: A Robust Attack Path Tracing Algorithm to Mitigate SYN-Flood DDoS Cyberattacks.

In the recent past, Distributed Denial of Service (DDoS) attacks have become more abundant and present one of the most serious security threats. In a DDoS attack, the attacker controls a botnet of daemons residing in vulnerable hosts that send a significant amount of traffic to flood the victim or the network infrastructure. In this paper, a common type of DDoS attacks known as "TCP SYN-Flood" is studied. This type of attack uses spoofed Internet Protocol (IP) addresses for SYN packets by exploiting the weakness in Transmission Control Protocol (TCP) 3-Way handshake used by the TCP/IP suite of protocols, which make the web servers unreachable for legitimate users or even worse, it might lead to server crash. In this paper, a resilient, efficient, lightweight, and robust IP traceback algorithm is proposed using an IP tracing packet for each attack path. The proposed algorithm suggests that edge routers-where the attack starts from-observe the traffic pattern passing through, and if the observed traffic carries the signature of TCP SYN-Flood DDoS attack and a high percentage of it is destined to a particular web server(s), it starts the tracing process by generating an IP trace packet, which accompanies the attack path recording the routers' IP addresses on the path between the attacker/daemon and the victim, which can extract the path and react properly upon receiving it by discarding any SYN packets originating from that attacker/daemon. To our knowledge, this is the first research that efficiently traces these kinds of attacks while they are running. The proposed solution has low computation and message overhead, efficient detection and tracing time, and converges in near optimal time. The results are validated using extensive simulation runs.